© 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. 11692
    Prev
    Next
    INDEX
    Explanations

    especially followed by important, useful, or nice

    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
    O
    0.71
    ແລະ
    0.65
     и
    0.60
    まったく
    0.57
    T
    0.56
    N
    0.55
    Р
    0.55
    あくまで
    0.55
     other
    0.55
    C
    0.54
    POSITIVE LOGITS
     wenn
    0.93
     όταν
    0.76
    when
    0.75
     when
    0.75
     Particularly
    0.74
     특히
    0.74
     cuando
    0.73
     jeśli
    0.72
     quando
    0.72
     besonders
    0.69
    Activations Density 0.064%

    No Known Activations