© 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-262K
    7. 108188
    Prev
    Next
    INDEX
    Explanations

    concepts and definitions

    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
    4
    0.62
    1
    0.57
     in
    0.53
    from
    0.51
    8
    0.51
    in
    0.50
    dataset
    0.50
    6
    0.48
    can
    0.48
    5
    0.47
    POSITIVE LOGITS
     homomorphisms
    0.56
     Encycl
    0.52
    ParamNum
    0.51
     pariy
    0.49
     Keci
    0.49
    alakip
    0.48
    óry
    0.48
    詄
    0.47
    ములో
    0.47
    พน
    0.46
    Activations Density 0.002%

    No Known Activations