© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1237
    Prev
    Next
    INDEX
    Explanations

    due to repeated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     a
    0.89
     this
    0.73
     the
    0.70
     to
    0.66
     b
    0.66
     many
    0.64
     for
    0.64
     in
    0.64
     one
    0.64
     m
    0.62
    POSITIVE LOGITS
    Ž
    0.78
     sqlType
    0.78
    PropertyParam
    0.76
    RetResult
    0.75
    Җ
    0.75
    원본파일명
    0.75
    StaticHandler
    0.74
     reqParams
    0.73
    ParamNum
    0.73
     desigualdad
    0.73
    Activations Density 0.119%

    No Known Activations