Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7589
    Prev
    Next
    INDEX
    Explanations

    player attributes and roles

    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_34/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
    şu
    -0.96
    ALING
    -0.87
    ENIE
    -0.82
    ———-
    -0.81
     robustness
    -0.81
    tettu
    -0.80
    verhalten
    -0.80
    ería
    -0.79
    pointer
    -0.79
    moment
    -0.79
    POSITIVE LOGITS
     cerebral
    1.06
     weapon
    0.98
     threats
    0.95
     born
    0.93
     commodity
    0.92
     weapons
    0.90
     focal
    0.89
     vocal
    0.87
     mold
    0.86
     option
    0.85
    Activations Density 0.024%

    No Known Activations