© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44646
    Prev
    Next
    INDEX
    Explanations

    proper names and foreign words

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

    This neuron responds to tokens that are parts of uppercase identifiers, acronyms, or proper‐name fragments.

    oai_token-act-pair · o4-miniTriggered 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
    {
    -3.41
    \
    -2.77
    ные
    -2.30
     essentials
    -2.27
    </b>
    -2.27
    UAWEI
    -2.25
     serían
    -2.25
     opr
    -2.23
     culmination
    -2.23
    ated
    -2.22
    POSITIVE LOGITS
    .”
    2.69
    ſelves
    2.42
     was
    2.41
     unquestionably
    2.39
     published
    2.34
    以上です
    2.33
    They
    2.33
     halted
    2.30
     believe
    2.27
     legitimately
    2.25
    Activations Density 0.190%

    No Known Activations