© 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. 14640
    Prev
    Next
    INDEX
    Explanations

    so followed by a clause

    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
     tört
    -2.39
    嫆
    -2.16
     impreso
    -2.08
    
    -2.08
     inverno
    -2.06
     unangemess
    -2.06
     összefoglal
    -2.02
    :”
    -2.02
     összefoglaló
    -1.98
    擽
    -1.95
    POSITIVE LOGITS
    '
    3.08
    ?
    2.67
    {
    2.33
    },
    2.31
     {
    2.25
     it
    2.19
    ',
    2.11
    \
    1.99
    *
    1.93
     before
    1.88
    Activations Density 0.019%

    No Known Activations