© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 160
    Prev
    Next
    INDEX
    Explanations

    Named principles and laws

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <unused169>
    0.42
     BasicDBObject
    0.42
     coerce
    0.40
    ColorBit
    0.40
    人民币
    0.38
     गठित
    0.38
    匏
    0.37
     Occurrence
    0.37
    reqParam
    0.37
    ূপে
    0.36
    POSITIVE LOGITS
    ian
    0.74
    ův
    0.71
    esque
    0.69
     Syndrome
    0.60
    定律
    0.55
     syndrome
    0.55
    氏
    0.54
     brothers
    0.53
     Brothers
    0.49
     theorem
    0.49
    Activations Density 0.079%

    No Known Activations