© 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. 41597
    Prev
    Next
    INDEX
    Explanations

    technical, programming, and descriptive contexts

    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
     It
    0.51
    s
    0.50
    in
    0.50
    na
    0.49
    CTION
    0.49
    Vari
    0.49
    Raw
    0.47
     Pack
    0.47
    Lo
    0.47
     Summ
    0.47
    POSITIVE LOGITS
    cdZ
    0.54
    ጷ
    0.52
     univariate
    0.50
     CCSDT
    0.49
     erlä
    0.48
    ildet
    0.47
     bivariate
    0.46
     aligns
    0.46
    Cadastro
    0.46
     môžu
    0.45
    Activations Density 0.001%

    No Known Activations