© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9119
    Prev
    Next
    INDEX
    Explanations

    shell and scripting commands

    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_16_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
    :
    0.57
     bungal
    0.56
     fright
    0.52
    बर्ग
    0.51
     ምን
    0.51
    間
    0.49
    es
    0.49
     בה
    0.49
     Chris
    0.48
    an
    0.48
    POSITIVE LOGITS
    Cyan
    0.51
    청
    0.50
    ﹁
    0.49
     pię
    0.49
     altri
    0.47
     abril
    0.47
     hicieron
    0.47
    лами
    0.47
    牞
    0.46
    פ
    0.46
    Activations Density 0.030%

    No Known Activations