© 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. 200030
    Prev
    Next
    INDEX
    Explanations

    specific nouns and adjectives

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

    making sense

    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
    ellular
    0.55
    Ꮺ
    0.54
    ﻉ
    0.51
    refour
    0.50
    ziehen
    0.49
    詳しく
    0.49
     ধরনের
    0.48
     कंपनियों
    0.48
     ಅಗತ್ಯ
    0.47
    ร
    0.47
    POSITIVE LOGITS
     call
    0.55
     snippet
    0.48
     prez
    0.48
     as
    0.47
     adjusted
    0.47
     trader
    0.47
     Deuter
    0.46
    发生在
    0.46
     easing
    0.45
     (
    0.45
    Activations Density 0.001%

    No Known Activations