© 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. 195644
    Prev
    Next
    INDEX
    Explanations

    direct marketing purposes

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

    code lines and extracted dates

    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
     scuole
    0.46
     vented
    0.46
     periodo
    0.44
    %]
    0.43
    ेंगू
    0.42
     tampilan
    0.42
     款
    0.42
     escritorio
    0.42
     fenomeno
    0.42
     plumb
    0.42
    POSITIVE LOGITS
    hofer
    0.41
     forfe
    0.39
    ジナ
    0.39
     കൊ
    0.39
    유
    0.39
    皇
    0.39
     Dum
    0.38
    რო
    0.38
     ছে
    0.38
    ucch
    0.38
    Activations Density 0.000%

    No Known Activations