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. 7709
    Prev
    Next
    INDEX
    Explanations

    more content than

    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
     pâ
    -0.96
     recue
    -0.96
     prea
    -0.93
     reais
    -0.93
    Papier
    -0.91
    Industrie
    -0.90
    bedien
    -0.88
     Diman
    -0.87
     efic
    -0.86
     veda
    -0.85
    POSITIVE LOGITS
     than
    2.05
    than
    1.41
     Than
    1.23
     niż
    1.20
    Than
    1.15
    Less
    1.07
     decât
    0.97
    ↵↵↵↵
    0.95
     Less
    0.94
     Fewer
    0.92
    Activations Density 0.060%

    No Known Activations