© 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. 11412
    Prev
    Next
    INDEX
    Explanations

    I and actions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    所に
    -1.17
    ttl
    -1.14
     jotka
    -1.02
    told
    -0.99
    oneof
    -0.98
    ༷
    -0.97
    fördert
    -0.96
    Told
    -0.96
    urther
    -0.93
    ˃
    -0.93
    POSITIVE LOGITS
     there
    1.29
     during
    1.20
     usually
    1.17
     certainly
    1.15
     only
    1.09
     about
    1.09
    これは
    1.08
     give
    1.05
     utilize
    1.03
     provide
    1.02
    Activations Density 0.094%

    No Known Activations