© 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. 22-GEMMASCOPE-RES-131K
    7. 129173
    Prev
    Next
    INDEX
    Explanations

    location, result, commission, friend, audit, market, stock, saved, rule, branch, attendance

    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_22/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
     проєкту
    -1.11
    bouts
    -1.09
     costuras
    -1.08
    toFloat
    -1.07
     проє
    -1.05
    」,
    -1.05
     eğitim
    -1.04
    Cambios
    -0.99
    わけで
    -0.99
     трябва
    -0.98
    POSITIVE LOGITS
    ?
    1.24
    c
    1.14
    ton
    1.14
    l
    1.06
     Commencez
    1.06
    line
    1.05
    g
    1.02
    impl
    1.01
    //
    1.01
    in
    1.01
    Activations Density 0.043%

    No Known Activations