© 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. 52747
    Prev
    Next
    INDEX
    Explanations

    candidates fit, contrast discrimination, completely uninstall

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

    instruction summarization

    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
    ll
    0.49
    details
    0.47
    rq
    0.45
    lew
    0.45
    li
    0.44
    address
    0.44
    datetime
    0.44
    6
    0.44
    pp
    0.44
    人群
    0.43
    POSITIVE LOGITS
     Nej
    0.53
    кость
    0.50
     trasc
    0.50
    燎
    0.47
     Trink
    0.46
     Bots
    0.45
    тика
    0.45
     Herbst
    0.45
    Ⴀ
    0.45
     Notas
    0.44
    Activations Density 0.000%

    No Known Activations