© 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. 36182
    Prev
    Next
    INDEX
    Explanations

    process

    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
    '
    0.80
    .
    0.75
    จะ
    0.74
    ile
    0.70
    or
    0.68
    the
    0.66
    ری
    0.64
     drows
    0.64
    in
    0.63
    เป็น
    0.63
    POSITIVE LOGITS
    g
    1.12
     процесс
    0.95
     Proces
    0.95
     процессы
    0.94
     processos
    0.90
    ع
    0.89
    గ
    0.89
     проце
    0.88
     processes
    0.88
    过程
    0.88
    Activations Density 0.063%

    No Known Activations