© 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. 38928
    Prev
    Next
    INDEX
    Explanations

    Totò, Tot, tot

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     stuks
    -2.53
    {
    -2.38
    ３
    -2.31
    The
    -2.27
    the
    -2.17
    Because
    -2.16
    </td>
    -2.13
    嚳
    -2.09
     tijden
    -2.06
     Where
    -1.98
    POSITIVE LOGITS
    髖
    2.33
    </strong>
    2.30
    図書館
    2.27
     to
    2.22
     dire
    2.16
    ⭓
    2.13
    婧
    2.11
     necessidades
    2.09
    P
    2.09
     we
    2.08
    Activations Density 0.000%

    No Known Activations