© 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. 10646
    Prev
    Next
    INDEX
    Explanations

    I, with name or title

    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
    烤
    1.95
    ленных
    1.81
     wizards
    1.76
     Turtles
    1.71
     turtles
    1.68
    吣
    1.67
     वेळा
    1.67
     আসামি
    1.66
    ecan
    1.65
     overlays
    1.64
    POSITIVE LOGITS
    흉
    1.71
    Amb
    1.68
    som
    1.65
    inst
    1.64
    innerHTML
    1.62
    kana
    1.60
    sal
    1.59
    뉴스
    1.58
    似
    1.58
    Downloads
    1.58
    Activations Density 0.002%

    No Known Activations