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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7942
    Prev
    Next
    INDEX
    Explanations

    software configuration and metadata

    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
    空格
    -0.95
     then
    -0.93
     frase
    -0.91
     getting
    -0.87
    manner
    -0.81
    leč
    -0.79
    hasilkan
    -0.78
     subsequently
    -0.78
    věr
    -0.77
     especially
    -0.77
    POSITIVE LOGITS
    "/>
    0.90
     propuestas
    0.88
    "/>
    
    0.87
    </
    0.87
     adecuado
    0.85
     añadido
    0.83
    abus
    0.83
     tweede
    0.82
     encapsulation
    0.82
     refuerzo
    0.82
    Activations Density 0.005%

    No Known Activations