© 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. 96889
    Prev
    Next
    INDEX
    Explanations

    medical, chemical, or ethical discussions

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

    solve system of equations

    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
    ле
    0.58
    не
    0.57
    스
    0.57
    Very
    0.54
    Ле
    0.54
    та
    0.54
    Amsterdam
    0.52
    Earnings
    0.50
    Sexy
    0.50
    тию
    0.49
    POSITIVE LOGITS
     poisons
    0.54
     ocas
    0.53
     instruments
    0.50
     ingred
    0.50
     minerales
    0.47
     regimens
    0.47
     ĝ
    0.47
    rochemical
    0.46
     that
    0.46
     animais
    0.46
    Activations Density 0.000%

    No Known Activations