© 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. 24932
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and separators

    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
     sés
    -1.26
     Decreto
    -1.23
     joyeux
    -1.22
    Объем
    -1.22
    Ȩ
    -1.21
     délic
    -1.20
     Agreg
    -1.17
    他們的
    -1.16
     arras
    -1.16
     Commentaires
    -1.15
    POSITIVE LOGITS
    claimer
    1.27
     Grüßen
    1.27
    </sup>
    1.23
     neither
    1.22
    strahlung
    1.20
     herido
    1.20
    changers
    1.18
    lifies
    1.17
    などは
    1.16
    rivial
    1.15
    Activations Density 0.004%

    No Known Activations