© 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. 232541
    Prev
    Next
    INDEX
    Explanations

    drive, summit, conditions

    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
     dirig
    0.59
    嬌
    0.57
    娇
    0.55
     municipalité
    0.52
     considere
    0.51
     lineNumber
    0.49
     jockey
    0.49
     shelved
    0.49
     unfilled
    0.48
     regering
    0.48
    POSITIVE LOGITS
    Conditions
    0.49
    case
    0.49
    ص
    0.48
    DM
    0.47
    된다
    0.46
    定义
    0.46
    想到
    0.45
    意思是
    0.45
    褶
    0.45
    defined
    0.45
    Activations Density 0.001%

    No Known Activations