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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 65249
    Prev
    Next
    INDEX
    Explanations

    multi-language support and offerings

    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_65k_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
     chival
    0.50
     genealog
    0.46
     барои
    0.44
    頗
    0.43
     Фурга
    0.43
     skirm
    0.43
     rôle
    0.43
     prima
    0.43
     véritable
    0.43
     heroic
    0.42
    POSITIVE LOGITS
    ov
    0.58
    g
    0.50
    io
    0.46
    但这
    0.45
    ă
    0.45
    row
    0.44
    co
    0.44
    ada
    0.44
    ir
    0.44
    ang
    0.44
    Activations Density 0.003%

    No Known Activations