© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72629
    Prev
    Next
    INDEX
    Explanations

    categories of things

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on plural count-noun labels (e.g. “species,” “studies,” “cities,” “agencies,” etc.), especially when used to enumerate or quantify groups.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    plural category nouns referring to large counted sets or enumerations, often in statistical or list contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    large numbers (typically in the thousands or higher) followed by plural nouns indicating quantity or scale.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -1.44
    ⓦ
    -1.24
    ولوژی
    -1.20
     miei
    -1.19
     extraordinaire
    -1.17
    ™.
    -1.17
    anadas
    -1.16
     этим
    -1.16
    дцать
    -1.16
     depois
    -1.15
    POSITIVE LOGITS
     to
    1.39
     verá
    1.33
     normalen
    1.27
     üblichen
    1.25
    Also
    1.23
     neuen
    1.23
     vanlig
    1.22
     aikaa
    1.20
     også
    1.19
     typical
    1.18
    Activations Density 0.142%

    No Known Activations