© 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. 11367
    Prev
    Next
    INDEX
    Explanations

    adding new items or improvements

    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
     ayaa
    -1.05
     rağmen
    -1.04
     préférable
    -0.97
    oprene
    -0.96
     udaler
    -0.96
     autobus
    -0.96
     türkiye
    -0.96
    schra
    -0.96
    zdo
    -0.95
    튤
    -0.93
    POSITIVE LOGITS
     bestanden
    0.93
    chures
    0.90
     e
    0.90
     also
    0.90
    ровано
    0.85
     open
    0.83
     slow
    0.81
     step
    0.81
     others
    0.80
    eab
    0.80
    Activations Density 0.002%

    No Known Activations