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. 8734
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and code snippets

    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
     in
    -1.14
     before
    -1.04
     Usually
    -1.03
     this
    -1.02
     but
    -0.97
     new
    -0.96
     from
    -0.95
     During
    -0.94
     své
    -0.94
     tocar
    -0.93
    POSITIVE LOGITS
     diverses
    0.93
     DUAL
    0.90
     INNOV
    0.90
     değiştir
    0.90
     facili
    0.89
     garten
    0.86
     quai
    0.86
     Dateien
    0.86
     hamilton
    0.86
     Dinas
    0.85
    Activations Density 0.000%

    No Known Activations