© 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. 97495
    Prev
    Next
    INDEX
    Explanations

    brightness, volts, page, example

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

    Analytical Engine, Cosa Nostra, LLMs

    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
    Kamol
    0.47
    چا
    0.47
    гка
    0.47
     Filmm
    0.47
    پ
    0.45
     philanthrop
    0.43
     Enrich
    0.43
     Humor
    0.42
    镰
    0.41
    Ein
    0.41
    POSITIVE LOGITS
     那麼
    0.52
     そんな
    0.48
     calcul
    0.47
    times
    0.46
     હોય
    0.46
     見
    0.45
     entidad
    0.45
    風景
    0.45
     Bogotá
    0.45
     biased
    0.44
    Activations Density 0.000%

    No Known Activations