© 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. 236269
    Prev
    Next
    INDEX
    Explanations

    From trick-or-treating to additional innovative

    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
     கடன்
    0.57
     어떻게
    0.54
    ية
    0.52
    پيديا
    0.50
     ดังนั้น
    0.50
    を用いて
    0.49
    ﻑ
    0.49
    楍
    0.49
    னம்
    0.48
    cısı
    0.48
    POSITIVE LOGITS
    0.59
     emocionante
    0.47
     wrong
    0.46
    wrong
    0.45
    ')";
    0.45
    KE
    0.45
    On
    0.43
    TP
    0.43
    PO
    0.43
    pok
    0.43
    Activations Density 0.001%

    No Known Activations