© 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. 26944
    Prev
    Next
    INDEX
    Explanations

    Data, Education, Focus, Consent, Artifact

    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
    眄
    0.54
    抉
    0.51
    푞
    0.46
    гноз
    0.46
    语
    0.46
    Sever
    0.46
    Semester
    0.46
    ห
    0.46
    Solved
    0.45
    مد
    0.45
    POSITIVE LOGITS
     punctuated
    0.52
     rounding
    0.50
     northbound
    0.50
     parentheses
    0.50
     periodic
    0.49
     nesting
    0.48
     Europa
    0.48
     NI
    0.48
     cobbl
    0.48
     Stokes
    0.47
    Activations Density 0.001%

    No Known Activations