© 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. 177507
    Prev
    Next
    INDEX
    Explanations

    lovely mares

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

    readability, usually, stirring, sequences, runs, cookies

    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
     براي
    0.50
     telefon
    0.50
     واقعی
    0.49
     ihnen
    0.48
     Banco
    0.48
    untuk
    0.48
    翌
    0.47
     Fernseh
    0.47
     Apakah
    0.46
     برای
    0.46
    POSITIVE LOGITS
    Contrib
    0.44
     avendo
    0.44
    Config
    0.43
    Vacc
    0.43
     instructing
    0.43
    ἱ
    0.43
    μέ
    0.42
    Psych
    0.41
    Princ
    0.40
    Winters
    0.40
    Activations Density 0.001%

    No Known Activations