© 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. 14120
    Prev
    Next
    INDEX
    Explanations

    where, when, how

    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
    define
    0.44
    .
    0.43
    xs
    0.42
    Count
    0.42
    FFECT
    0.41
    4
    0.41
    begin
    0.41
    。
    0.40
    rho
    0.40
    定義
    0.40
    POSITIVE LOGITS
     ugyan
    0.46
    тың
    0.44
     Kyr
    0.44
     triumphs
    0.44
     pleasantly
    0.43
    鍮
    0.43
    이지만
    0.43
     Issled
    0.43
     delicios
    0.42
     delightfully
    0.41
    Activations Density 0.015%

    No Known Activations