© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3149
    Prev
    Next
    INDEX
    Explanations

    writing csv files as

    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_7_width_16k_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
    н
    2.24
    an
    1.96
    y
    1.90
    oos
    1.75
    ي
    1.74
    en
    1.71
    er
    1.70
    enst
    1.67
    ة
    1.65
    oes
    1.62
    POSITIVE LOGITS
    AnalyzeAction
    2.18
    È
    2.03
    展览
    1.93
     LikeLike
    1.91
     Partners
    1.87
    ---------*/
    1.85
     Receivable
    1.83
    Ố
    1.82
     Assistants
    1.82
     reqParams
    1.82
    Activations Density 0.007%

    No Known Activations