© 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. 103497
    Prev
    Next
    INDEX
    Explanations

    lists phrases and associated topics

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

    within or without

    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
     頭
    0.57
     発
    0.56
     เอา
    0.53
    <unused2186>
    0.51
     透明
    0.51
     顔
    0.50
     ครู
    0.49
    <unused713>
    0.48
     Halke
    0.48
    olot
    0.48
    POSITIVE LOGITS
     SOLAR
    0.44
    ically
    0.44
     within
    0.43
     clause
    0.43
     safely
    0.42
     থাকলেও
    0.42
     for
    0.42
     only
    0.42
     documents
    0.42
     provides
    0.41
    Activations Density 0.000%

    No Known Activations