© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139563
    Prev
    Next
    INDEX
    Explanations

    core informational structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kyll
    0.54
     Elbow
    0.49
    頖
    0.49
     Lunch
    0.48
    梆
    0.48
    愴
    0.48
     Dinner
    0.47
     जितेंद्र
    0.47
     Community
    0.47
    getFlight
    0.46
    POSITIVE LOGITS
    istern
    0.55
    is
    0.51
    ar
    0.48
    트
    0.47
    isme
    0.46
    ivet
    0.45
    iour
    0.44
    rés
    0.44
    re
    0.43
    in
    0.43
    Activations Density 0.000%

    No Known Activations