© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92378
    Prev
    Next
    INDEX
    Explanations

    fishing results

    np_acts-logits-general · gemini-2.5-flash-lite

    gaps, sickness, fatigue, change, rising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    毫无
    0.49
     egregious
    0.47
    迷惑
    0.47
    涩
    0.46
    乃至
    0.45
    疼痛
    0.45
    紧张
    0.45
    如有
    0.44
    汐
    0.44
    ENCIA
    0.44
    POSITIVE LOGITS
     forme
    0.57
     finishing
    0.54
     Trader
    0.54
     भारता
    0.53
     post
    0.52
     colleague
    0.50
     co
    0.49
     Indian
    0.49
     NAO
    0.48
     Lists
    0.48
    Activations Density 0.001%

    No Known Activations