© 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. 38309
    Prev
    Next
    INDEX
    Explanations

    determiner + specific noun/adjective

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

    fats and acids

    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
    eing
    0.62
    cosec
    0.55
    ir
    0.53
    aing
    0.52
    aporation
    0.51
    ccco
    0.51
    ciamo
    0.50
    ż
    0.50
    ジナル
    0.49
    ၀
    0.49
    POSITIVE LOGITS
     kanker
    0.48
    Assembly
    0.45
    SuppressWarnings
    0.45
    PO
    0.44
    TorpedoStore
    0.44
    ARG
    0.43
    DELETE
    0.43
    GRAY
    0.42
    ^{*}\
    0.41
    AC
    0.41
    Activations Density 0.000%

    No Known Activations