© 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. 67146
    Prev
    Next
    INDEX
    Explanations

    character descriptions and roles

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

    The neuron fires strongly on mentions of “character” (and its variants), i.e. references to roles or characters.

    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
    </em>
    -1.52
     from
    -1.20
     DEFEND
    -1.12
    तु
    -1.12
    ödie
    -1.09
    鸶
    -1.09
     saveurs
    -1.08
    usahaan
    -1.08
     quienes
    -1.07
     vũ
    -1.06
    POSITIVE LOGITS
     ‘‘
    1.95
     {
    1.74
     ‘’
    1.45
    ՝
    1.45
     ۳
    1.42
    called
    1.40
     ‘
    1.35
    ,’
    1.34
     casada
    1.30
     “
    1.29
    Activations Density 0.017%

    No Known Activations