© 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. 246261
    Prev
    Next
    INDEX
    Explanations

    years of publication

    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
    ENN
    0.45
     man
    0.44
    主席
    0.43
    inais
    0.41
     Président
    0.39
    ли
    0.39
    牡
    0.39
     policemen
    0.38
     காவல்துற
    0.38
    frc
    0.38
    POSITIVE LOGITS
     eccess
    0.48
    ကို
    0.47
     "~/
    0.46
     পৃ
    0.45
    လုံး
    0.45
    になると
    0.45
    atanga
    0.45
    긱
    0.44
    ബാ
    0.44
    にっいて
    0.44
    Activations Density 0.001%

    No Known Activations