© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12380
    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
    an
    -1.27
    in
    -1.13
    着一个
    -1.08
    DBL
    -1.08
     IN
    -1.07
    🌱
    -1.03
     augusti
    -1.01
    损坏
    -1.00
    💓
    -1.00
    stdio
    -1.00
    POSITIVE LOGITS
    完成です
    1.18
    jandro
    1.11
     nuovamente
    1.09
    或者
    1.08
     wüns
    1.05
     mão
    1.04
     eccell
    1.02
     ricca
    1.02
     stava
    1.01
     sicuramente
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.