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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65619
    Prev
    Next
    INDEX
    Explanations

    at your option

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

    The neuron consistently lights up on the two‐letter substring “is” (and similarly “at”) wherever it appears in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     DISCUSS
    -0.74
    neos
    -0.72
     recém
    -0.71
    扮
    -0.70
    read
    -0.66
    瘠
    -0.66
     einz
    -0.66
     taus
    -0.65
     disposto
    -0.65
     read
    -0.65
    POSITIVE LOGITS
    ByteArray
    0.70
    ляет
    0.68
    Ari
    0.68
    ندي
    0.68
    amide
    0.67
    omitempty
    0.66
     kisses
    0.66
     Mawr
    0.65
     มา
    0.65
    Aber
    0.65
    Activations Density 0.089%

    No Known Activations