© 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. 3173
    Prev
    Next
    INDEX
    Explanations

    versions of files or concepts

    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
     절대
    0.45
     ಸಾಮಾನ್ಯ
    0.44
    ξης
    0.44
    に行く
    0.44
    rischen
    0.44
    &$\
    0.43
     optimality
    0.43
     ಇದ
    0.43
     понять
    0.42
     유명
    0.42
    POSITIVE LOGITS
     are
    0.47
     unat
    0.46
    سلم
    0.46
     Of
    0.45
     tél
    0.43
    Clothes
    0.43
    с
    0.43
     थीं
    0.42
     Cities
    0.42
     tê
    0.42
    Activations Density 0.000%

    No Known Activations