© 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. 12359
    Prev
    Next
    INDEX
    Explanations

    somewhere else or density of

    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
    ে
    3.72
    ੀ
    3.60
     '**
    3.21
    yyyyyyyy
    3.16
    𝒆
    3.15
    ી
    3.07
    lardan
    2.97
    راب
    2.93
    هداف
    2.91
    yj
    2.87
    POSITIVE LOGITS
    ح
    2.52
    ك
    2.39
    с
    2.29
    د
    2.23
    ுகள்
    2.20
    cr
    2.18
     pr
    2.16
    วน
    2.13
    ب
    2.11
    حول
    2.10
    Activations Density 0.019%

    No Known Activations