© 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. 34-GEMMASCOPE-RES-131K
    7. 109905
    Prev
    Next
    INDEX
    Explanations

    process improvement

    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
     صدي
    -0.89
    ogh
    -0.86
    screenWidth
    -0.84
    теше
    -0.79
    简约
    -0.78
    Nob
    -0.77
    Eid
    -0.77
    фессиона
    -0.76
     dużo
    -0.76
    offrir
    -0.76
    POSITIVE LOGITS
     Pareto
    0.98
     workplace
    0.96
     TPM
    0.89
     team
    0.87
    職場
    0.85
     Ka
    0.85
     area
    0.85
    matplotlib
    0.83
     equipment
    0.82
     standardized
    0.82
    Activations Density 0.006%

    No Known Activations