© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12439
    Prev
    Next
    INDEX
    Explanations

    explicit content

    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
    𝙙
    2.05
    ㄞ
    1.96
     resonate
    1.95
    芻
    1.93
    𝒹
    1.90
    voren
    1.90
    munder
    1.85
    fet
    1.83
    gür
    1.83
    bruk
    1.82
    POSITIVE LOGITS
    مس
    1.77
    াবহ
    1.62
     essa
    1.61
    Одна
    1.60
    вЂ
    1.59
    izedBox
    1.59
    ۀ
    1.58
    $^
    1.53
    Й
    1.53
     રાખ
    1.52
    Activations Density 6.361%

    No Known Activations