© 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. 222240
    Prev
    Next
    INDEX
    Explanations

    telephone, search, how, done

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

    punctuation and special characters

    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
    isjon
    0.44
     VERY
    0.44
     Buckeyes
    0.44
    ifically
    0.43
     നേടി
    0.43
     لدينا
    0.43
     เมตร
    0.42
     န
    0.42
     هيبقى
    0.42
     picks
    0.42
    POSITIVE LOGITS
    除
    0.50
    haltung
    0.47
    㽛
    0.46
    ो
    0.45
    প্র
    0.45
    Much
    0.41
    و
    0.41
     বা
    0.41
     or
    0.40
     સમગ્ર
    0.40
    Activations Density 0.001%

    No Known Activations