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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 421
    Prev
    Next
    INDEX
    Explanations

    ethical guidelines and limitations

    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
    -
    1.53
    cre
    1.52
    ve
    1.51
    as
    1.47
    .
    1.46
    os
    1.46
    (
    1.45
    nel
    1.44
    con
    1.42
    vation
    1.41
    POSITIVE LOGITS
    ंगाबाद
    2.49
    laquo
    2.36
    REW
    2.11
     hatta
    2.08
     wszyscy
    1.97
    খানেই
    1.95
    yacute
    1.95
    <unused1799>
    1.93
    <unused719>
    1.92
    scaron
    1.91
    Activations Density 1.216%

    No Known Activations