© 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. 10-GEMMASCOPE-RES-131K
    7. 72031
    Prev
    Next
    INDEX
    Explanations

    professional roles and 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_10/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
     we
    -1.30
    Теперь
    -1.23
     Señor
    -1.21
    (()
    -1.21
    तिहास
    -1.20
     herein
    -1.20
    看去
    -1.20
     såsom
    -1.18
     deltag
    -1.16
     negocio
    -1.15
    POSITIVE LOGITS
     about
    1.43
     thậm
    1.29
     sogar
    1.27
     péro
    1.24
     навіть
    1.22
    пример
    1.18
     dichos
    1.16
     նաև
    1.16
     vardı
    1.15
     dichas
    1.15
    Activations Density 0.404%

    No Known Activations