© 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. 64722
    Prev
    Next
    INDEX
    Explanations

    training models and learning

    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
    ים
    0.80
     İng
    0.73
     venden
    0.70
    ﺘ
    0.67
    ฟ้า
    0.67
     denounce
    0.67
    امي
    0.66
    ેચ્છ
    0.66
     financière
    0.66
    ারে
    0.65
    POSITIVE LOGITS
    w
    0.83
    x
    0.74
    q
    0.74
    o
    0.71
    ng
    0.68
    ish
    0.68
    pp
    0.67
    ched
    0.66
    inds
    0.66
    ane
    0.66
    Activations Density 0.082%

    No Known Activations