© 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. 45218
    Prev
    Next
    INDEX
    Explanations

    group, tables, tabs, fractions, objects

    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
     in
    -1.05
     يساعد
    -0.93
     feat
    -0.93
    зив
    -0.92
    幾乎
    -0.89
     annet
    -0.88
    Manfaat
    -0.88
     anderer
    -0.87
     him
    -0.87
     both
    -0.86
    POSITIVE LOGITS
     you
    1.38
     that
    1.09
    气氛
    1.07
    claimer
    1.02
    ális
    0.97
     were
    0.96
     இந்த
    0.96
    doise
    0.96
     inclusief
    0.96
    شارة
    0.96
    Activations Density 0.219%

    No Known Activations