© 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. 3466
    Prev
    Next
    INDEX
    Explanations

    Gents –

    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
     ARTICLES
    2.50
     `{
    2.42
     НЕ
    2.39
     Ве
    2.33
     令
    2.32
     PARTIC
    2.30
     除了
    2.29
     "-//
    2.29
     ""<
    2.27
     WHIT
    2.26
    POSITIVE LOGITS
    a
    2.24
    o
    2.17
    am
    2.13
    an
    2.03
    al
    2.00
    os
    1.87
    as
    1.83
    et
    1.77
    es
    1.76
    -
    1.73
    Activations Density 0.084%

    No Known Activations