© 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. 17154
    Prev
    Next
    INDEX
    Explanations

    numbers, app updates, or actions

    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
     far
    0.46
    v
    0.45
    0.44
    <b>
    0.43
     view
    0.43
    [
    0.42
    Here
    0.42
    #
    0.42
    T
    0.41
     la
    0.41
    POSITIVE LOGITS
    eluarkan
    0.53
     Сурикова
    0.52
    ChessBot
    0.50
    宒
    0.50
    <unused584>
    0.50
     manglid
    0.50
    oppositions
    0.50
     cervello
    0.50
    <unused1903>
    0.49
    гов
    0.49
    Activations Density 0.003%

    No Known Activations