© 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. 12095
    Prev
    Next
    INDEX
    Explanations

    recollection, canisters, tabletop, freezer

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

    atmosphere, negation, or specific services

    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
    Ii
    0.54
    Prove
    0.53
    ьи
    0.52
    GPI
    0.48
    ഗ
    0.46
    AS
    0.46
    フレ
    0.46
    ー
    0.45
    Õ
    0.45
     idiots
    0.45
    POSITIVE LOGITS
     వే
    0.46
     Ба
    0.46
     Fusion
    0.46
     Consume
    0.46
     Во
    0.45
    ኗ
    0.45
     Beiträge
    0.44
     Bat
    0.43
     Fisheries
    0.43
     Semua
    0.42
    Activations Density 0.000%

    No Known Activations