© 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. 71612
    Prev
    Next
    INDEX
    Explanations

    Sandy railway, Chronic conditions, Demand flow

    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
    也在
    -1.66
     onsdag
    -1.65
     torsdag
    -1.65
     velkommen
    -1.62
     medarbe
    -1.58
     medlems
    -1.57
    场的
    -1.55
    打的
    -1.54
     ingenting
    -1.52
     alltid
    -1.51
    POSITIVE LOGITS
     then
    1.92
     a
    1.75
    當時
    1.62
     atmosf
    1.58
     at
    1.55
     their
    1.55
     his
    1.53
     now
    1.51
     with
    1.47
    他們的
    1.46
    Activations Density 0.000%

    No Known Activations