© 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. 127680
    Prev
    Next
    INDEX
    Explanations

    compliance, insurance, countries

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

    translate languages, earn, escape

    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
    })}{\
    0.47
    <0xAE>
    0.45
    имо
    0.45
    ította
    0.45
     Trotsky
    0.44
     Levy
    0.43
     रॉय
    0.43
     bub
    0.43
    rios
    0.43
    嘖
    0.43
    POSITIVE LOGITS
    大切な
    0.55
    G
    0.50
    Png
    0.48
    IT
    0.48
    Nes
    0.47
    Index
    0.46
    Age
    0.46
     climbed
    0.46
    aas
    0.46
    Insurance
    0.46
    Activations Density 0.000%

    No Known Activations