© 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. 3147
    Prev
    Next
    INDEX
    Explanations

    at its or at the

    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
    erar
    3.43
    issive
    2.88
    ுள்ளனர்
    2.78
    گار
    2.76
    ுள்ளார்
    2.69
    羡
    2.69
    ోతి
    2.63
    umlahan
    2.58
    墟
    2.57
    еры
    2.57
    POSITIVE LOGITS
    ty
    4.01
    tttt
    3.67
    ting
    3.61
    ttt
    3.60
    ten
    3.41
    te
    3.25
    ⣶
    3.08
    hetically
    3.07
    ched
    3.02
    riot
    2.97
    Activations Density 0.697%

    No Known Activations