© 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. 55649
    Prev
    Next
    INDEX
    Explanations

    using each, near misses, the city

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

    intuition, desired, repeat ends, capacitive, California Institute

    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
    اث
    0.48
    ар
    0.47
    提起
    0.46
    вому
    0.45
    ﺶ
    0.44
    USER
    0.44
    EXPL
    0.44
    染
    0.44
    ян
    0.44
    attuale
    0.43
    POSITIVE LOGITS
     menyenangkan
    0.53
     ikut
    0.51
     Valentines
    0.51
     offici
    0.48
     princesses
    0.48
     Spacious
    0.47
     dành
    0.46
     Tsuen
    0.46
     छुट्टियों
    0.46
     seulement
    0.45
    Activations Density 0.000%

    No Known Activations