© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 53338
    Prev
    Next
    INDEX
    Explanations

    independent research

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

    operational efficiency

    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
    ion
    0.52
    ies
    0.47
    als
    0.47
     ""}
    0.45
     soften
    0.44
     সবচেয়ে
    0.43
    es
    0.42
     කළ
    0.42
    മുള്ള
    0.42
     meest
    0.42
    POSITIVE LOGITS
     Equip
    0.48
    CHR
    0.43
    bedarf
    0.42
     بتر
    0.41
    装备
    0.41
    淼
    0.40
    വിഡ്
    0.39
    完毕
    0.39
    延长
    0.39
    кви
    0.39
    Activations Density 0.000%

    No Known Activations