© 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. 27748
    Prev
    Next
    INDEX
    Explanations

    why and typical explanations

    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
    1
    0.50
    [
    0.43
     commitments
    0.42
    (
    0.42
     //[
    0.41
    餬
    0.41
    bbene
    0.40
     Reforms
    0.39
    2
    0.39
     eten
    0.38
    POSITIVE LOGITS
    ប្រតិ
    0.50
    MenuStyle
    0.49
    푞
    0.48
    TextColor
    0.47
    മുഖ
    0.47
    有り
    0.45
    ◜
    0.45
    ახებ
    0.45
    下去
    0.44
    rzez
    0.44
    Activations Density 0.005%

    No Known Activations