© 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. 73025
    Prev
    Next
    INDEX
    Explanations

    code structure and definitions

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

    static int / C++ code

    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
     nyeri
    0.43
     مؤثر
    0.43
     centre
    0.40
    Deck
    0.39
    贓
    0.39
     Centro
    0.38
     изме
    0.38
     ಕೇಂದ್ರ
    0.38
     CENTRE
    0.38
     санти
    0.38
    POSITIVE LOGITS
    öffentlichung
    0.44
    assertion
    0.44
    dependence
    0.42
     tentative
    0.41
    诋
    0.40
    წყ
    0.40
    approximation
    0.39
    entropy
    0.39
    їв
    0.38
     Gordon
    0.38
    Activations Density 0.004%

    No Known Activations