© 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. 12362
    Prev
    Next
    INDEX
    Explanations

    comparison and difference

    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
     olvidado
    -0.98
     véhic
    -0.93
    ayuda
    -0.91
    isbury
    -0.90
     coûts
    -0.89
     ônibus
    -0.88
    ônio
    -0.86
    mutlich
    -0.85
     déliv
    -0.84
     Conseils
    -0.84
    POSITIVE LOGITS
     compared
    1.35
     versus
    1.05
    Compared
    1.01
    vs
    0.97
     Compared
    0.96
    versus
    0.94
     vs
    0.93
    Me
    0.93
    ختلف
    0.93
    Override
    0.90
    Activations Density 0.015%

    No Known Activations