© 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. 22-GEMMASCOPE-RES-131K
    7. 16523
    Prev
    Next
    INDEX
    Explanations

    technical concepts and specific contexts

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    It
    -1.07
     on
    -0.99
    H
    -0.92
    くれます
    -0.91
    lné
    -0.88
    CCO
    -0.88
    r
    -0.87
     two
    -0.86
    W
    -0.85
    c
    -0.85
    POSITIVE LOGITS
     pomaga
    1.20
     apprécier
    1.12
     écouter
    1.10
     belangrijke
    1.10
     kontaktu
    1.10
     Reſ
    1.09
     empêcher
    1.09
     ayudan
    1.09
     étudier
    1.08
     opções
    1.07
    Activations Density 0.080%

    No Known Activations