© 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. 15042
    Prev
    Next
    INDEX
    Explanations

    specific languages or topics

    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
    낀
    0.43
    何か
    0.40
     ਜਾਂ
    0.40
    льну
    0.39
    もしくは
    0.39
    信用
    0.39
     بونس
    0.38
     singularly
    0.38
     COMMISSION
    0.38
    謗
    0.38
    POSITIVE LOGITS
     n
    0.47
    ab
    0.47
     gelecek
    0.46
    ī
    0.46
     music
    0.46
    ang
    0.46
    aman
    0.46
     again
    0.44
     IComparable
    0.44
    ö
    0.44
    Activations Density 0.004%

    No Known Activations