© 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. 132608
    Prev
    Next
    INDEX
    Explanations

    lists of authors

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

    scale, quantity, card, table

    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
     এসেছেন
    0.45
    ↵
    0.44
    bandage
    0.44
    𝙄
    0.43
     bestaan
    0.43
     semillas
    0.42
     adoptar
    0.42
    basin
    0.42
     ਬਾ
    0.42
     স্বাধীন
    0.41
    POSITIVE LOGITS
     tete
    0.48
    欹
    0.47
    ూరు
    0.46
     इसको
    0.45
     इनको
    0.45
    irchen
    0.45
    者を
    0.45
    丁目
    0.43
    itches
    0.42
     yoki
    0.42
    Activations Density 0.000%

    No Known Activations