© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148007
    Prev
    Next
    INDEX
    Explanations

    investing time and guiding others

    np_acts-logits-general · gemini-2.5-flash-lite

    indicate approximate identify schedule reducing parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    in
    0.52
     ب
    0.50
     in
    0.49
    this
    0.49
     Agro
    0.47
     at
    0.46
     Ne
    0.45
     that
    0.44
     Per
    0.43
     software
    0.43
    POSITIVE LOGITS
    🧖
    0.57
     paździer
    0.51
    gqlgen
    0.50
    🎸
    0.50
    🚇
    0.50
     berikutnya
    0.49
    시킨
    0.49
     পয়
    0.49
    alkoz
    0.48
     pakaian
    0.48
    Activations Density 0.000%

    No Known Activations