© 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. 40728
    Prev
    Next
    INDEX
    Explanations

    diagrams and structural elements

    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
    訒
    0.49
    ങ്ങളുടെ
    0.48
     possibile
    0.47
     generasi
    0.47
    フィック
    0.46
     latitudine
    0.45
     tekanan
    0.45
    াদান
    0.44
    ærer
    0.44
    詃
    0.44
    POSITIVE LOGITS
     C
    0.45
    mao
    0.44
    wide
    0.43
     B
    0.41
    Full
    0.41
     미
    0.41
     Prolong
    0.41
    D
    0.41
    Qu
    0.41
     литературы
    0.41
    Activations Density 0.002%

    No Known Activations