Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 7777
    Prev
    Next
    INDEX
    Explanations

    lists with ratings and scores

    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
     débit
    0.52
    補充
    0.47
     atvej
    0.46
     disturb
    0.46
     sprem
    0.46
    霽
    0.46
     revest
    0.45
     revêt
    0.45
     appelé
    0.44
     grim
    0.44
    POSITIVE LOGITS
    na
    0.66
    5
    0.55
    6
    0.54
    s
    0.52
    ni
    0.51
    st
    0.51
    ¢
    0.51
    ne
    0.50
    7
    0.49
    Careers
    0.48
    Activations Density 0.001%

    No Known Activations