© 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. 10704
    Prev
    Next
    INDEX
    Explanations

    stretching, flexibility, rent, vision, neck

    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
     atoms
    1.59
    <unused1766>
    1.56
     glaciers
    1.54
    CurrentImage
    1.54
    ègre
    1.53
    uvial
    1.53
     rivers
    1.53
     waterways
    1.51
     pathogens
    1.50
     secreted
    1.46
    POSITIVE LOGITS
    s
    1.07
    และ
    1.06
    tive
    1.05
    Tek
    1.04
     дум
    1.02
     и
    0.98
    and
    0.98
    ומי
    0.97
     Especial
    0.96
    /
    0.96
    Activations Density 0.474%

    No Known Activations