© 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. 112754
    Prev
    Next
    INDEX
    Explanations

    names after commas

    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
     réve
    -2.11
     préférence
    -2.08
     verrou
    -2.06
     régal
    -2.03
     tromper
    -1.82
     gouttes
    -1.78
     sécher
    -1.78
     cuisson
    -1.70
    Karakteristik
    -1.70
     horaire
    -1.68
    POSITIVE LOGITS
     and
    2.75
     including
    2.09
     between
    2.03
     from
    1.98
     to
    1.95
     while
    1.93
     along
    1.92
     will
    1.84
     in
    1.80
     a
    1.80
    Activations Density 0.002%

    No Known Activations