© 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. 76827
    Prev
    Next
    INDEX
    Explanations

    assembly, Constantine, marathon

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

    blockchain addresses and wallets

    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
    H
    0.57
    Y
    0.57
    light
    0.54
    iling
    0.53
    te
    0.53
    G
    0.52
    ll
    0.52
    ne
    0.52
    ysk
    0.52
    K
    0.52
    POSITIVE LOGITS
    সভা
    0.52
     डिटे
    0.48
     لأن
    0.47
     authToken
    0.47
    टरीना
    0.47
     cuya
    0.46
     escenarios
    0.46
     cuyo
    0.45
     cuánt
    0.45
     míst
    0.44
    Activations Density 0.000%

    No Known Activations