© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92022
    Prev
    Next
    INDEX
    Explanations

    export and import laws

    np_acts-logits-general · gemini-2.5-flash-lite

    export, taking, or posting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    աջ
    0.44
    ните
    0.43
    缰
    0.43
    Investor
    0.42
     maturity
    0.41
     caramel
    0.41
     효과
    0.41
    ната
    0.40
    ליה
    0.40
     bättre
    0.39
    POSITIVE LOGITS
     dictum
    0.49
    شب
    0.44
     Webster
    0.44
    strates
    0.43
    ⅼ
    0.43
    <unused1864>
    0.42
    gebaut
    0.42
     Generators
    0.42
     valable
    0.42
    >
    0.41
    Activations Density 0.000%

    No Known Activations