© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30216
    Prev
    Next
    INDEX
    Explanations

    prefixes of capitalized words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Perhaps
    -0.88
    Unidad
    -0.81
    Although
    -0.80
     although
    -0.79
    ～。
    -0.77
    entech
    -0.77
     exigir
    -0.76
    Probably
    -0.75
    وفر
    -0.75
     continuará
    -0.75
    POSITIVE LOGITS
     nonatomic
    0.96
     Valence
    0.92
    バリー
    0.88
     Schülerinnen
    0.87
     atoms
    0.86
    originally
    0.85
     タイ
    0.85
     brimming
    0.84
    positional
    0.84
    BO
    0.83
    Activations Density 0.009%

    No Known Activations