© 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. 168538
    Prev
    Next
    INDEX
    Explanations

    foreign words including perfect

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

    hacker, attacker, controls

    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
    тися
    0.50
    רי
    0.50
    聯繫
    0.49
    疊
    0.47
    ז
    0.47
    産業
    0.47
    絃
    0.47
    רו
    0.46
    を発
    0.45
    據
    0.45
    POSITIVE LOGITS
     indelible
    0.50
     tasteful
    0.50
     片
    0.48
    RefreshToken
    0.48
     perfekt
    0.48
     perfecta
    0.48
     осве
    0.48
     vand
    0.46
    不错的
    0.46
     kebab
    0.46
    Activations Density 0.000%

    No Known Activations