© 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. 10627
    Prev
    Next
    INDEX
    Explanations

    push-ups, like fuzzy feelings

    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
    Ầ
    2.21
    JJ
    2.18
    ThemeOverlay
    2.14
    GetOffset
    2.08
    ngày
    2.06
     vài
    2.04
     imprensa
    2.01
    营业
    2.00
    欢
    2.00
    Ông
    1.99
    POSITIVE LOGITS
    ي
    2.45
    ations
    1.96
    ות
    1.95
    ্যক
    1.89
     elevations
    1.82
    iagn
    1.82
    ة
    1.80
     morphism
    1.79
    al
    1.78
    owski
    1.77
    Activations Density 0.004%

    No Known Activations