© 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. 12265
    Prev
    Next
    INDEX
    Explanations

    legal citations and names

    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
     člove
    -0.96
     materialen
    -0.94
     Američ
    -0.93
     Kiedy
    -0.89
     mencionar
    -0.88
     šte
    -0.87
    During
    -0.87
     favorece
    -0.87
     όταν
    -0.87
     Schicks
    -0.86
    POSITIVE LOGITS
     fz
    0.85
     kW
    0.85
     刻
    0.83
    🏈
    0.83
    
    0.82
    wants
    0.82
    低的
    0.82
     comedia
    0.81
     lbs
    0.81
    raft
    0.81
    Activations Density 0.044%

    No Known Activations