© 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. 25850
    Prev
    Next
    INDEX
    Explanations

    lawlessness increasing

    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
     ஓடுப
    0.52
     daly
    0.50
    ersburg
    0.48
    ící
    0.47
    ņ
    0.47
     관광
    0.46
    ’
    0.46
    🅔
    0.44
    Ị
    0.44
    ioni
    0.44
    POSITIVE LOGITS
    我
    0.57
    新
    0.52
    、
    0.47
     (
    0.44
    setTime
    0.44
    陳
    0.44
     मुद्दों
    0.43
    Direct
    0.43
    রস
    0.43
    最初
    0.42
    Activations Density 0.001%

    No Known Activations