© 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. 47067
    Prev
    Next
    INDEX
    Explanations

    rarely says or few

    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
    Negative Logits
     variously
    -1.36
    ciale
    -1.13
     либо
    -1.09
    esseurs
    -1.03
     piuttosto
    -1.03
    LOGIN
    -1.02
    Почему
    -0.99
    зно
    -0.98
    robo
    -0.98
    addGap
    -0.98
    POSITIVE LOGITS
     actually
    1.90
     truly
    1.87
     verdaderamente
    1.52
     any
    1.50
     actual
    1.46
     tatsächlich
    1.43
    真正
    1.43
     genuinely
    1.43
    Actually
    1.38
     wirklich
    1.36
    Activations Density 0.047%

    No Known Activations