© 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. 3291
    Prev
    Next
    INDEX
    Explanations

    legal consequences and prison sentences

    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
    s
    1.92
    ΗΣ
    1.85
    晗
    1.84
    л
    1.83
    ੀ
    1.72
     যায়
    1.69
    ುದು
    1.68
    CLR
    1.68
     ප්‍ර
    1.63
    ר
    1.63
    POSITIVE LOGITS
    ogenetic
    2.57
    ewomen
    2.23
     alluvial
    2.23
    ători
    2.19
     canoes
    2.16
    isphere
    2.13
    ofan
    2.10
    oplastic
    2.10
    residents
    2.09
     perennials
    2.08
    Activations Density 0.000%

    No Known Activations