© 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. 109851
    Prev
    Next
    INDEX
    Explanations

    model of models and conversions

    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
    ژاد
    -0.81
    Recursos
    -0.77
    ፅ
    -0.73
     Mexicans
    -0.71
     flocked
    -0.69
    Formato
    -0.68
    DANGER
    -0.68
     azi
    -0.68
     aptitudes
    -0.68
    model
    -0.65
    POSITIVE LOGITS
     конвер
    1.08
     scratch
    1.02
     conversions
    0.98
     conversion
    0.94
     Conversions
    0.93
     converted
    0.87
     box
    0.85
     Conversion
    0.84
    painted
    0.84
     plomo
    0.83
    Activations Density 0.021%

    No Known Activations