© 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. 71321
    Prev
    Next
    INDEX
    Explanations

    conditional then-statements

    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
    de
    0.83
    or
    0.79
    ur
    0.77
    ing
    0.73
    6
    0.73
    al
    0.70
    7
    0.69
    ir
    0.69
    5
    0.69
    he
    0.68
    POSITIVE LOGITS
    на
    0.61
    مس
    0.55
    此
    0.54
    มัน
    0.54
    رفة
    0.54
    ს
    0.54
     eyesight
    0.53
     udało
    0.52
    서는
    0.50
    наў
    0.50
    Activations Density 0.007%

    No Known Activations