Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11651
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     noire
    -1.11
     taux
    -1.04
    Ꮂ
    -1.02
     raisons
    -1.00
     benne
    -1.00
    🔧
    -0.98
    Fahren
    -0.98
    Celsius
    -0.96
    🗓
    -0.95
     souris
    -0.94
    POSITIVE LOGITS
     навіть
    1.37
     describe
    1.21
     realizará
    1.19
     contextLoads
    1.16
     are
    1.13
     Versuche
    1.12
     даже
    1.10
     Angeb
    1.09
     nawet
    1.09
     cannot
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.