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. 7846
    Prev
    Next
    INDEX
    Explanations

    numbers enclosed in parentheses

    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
     falling
    -0.85
    Falling
    -0.78
    落地
    -0.75
     Falling
    -0.75
    Apparatus
    -0.74
     Deniz
    -0.73
    льне
    -0.71
     liet
    -0.71
    ódź
    -0.71
     fall
    -0.71
    POSITIVE LOGITS
    манда
    0.80
     licenci
    0.79
     team
    0.78
    grey
    0.73
    ⋆
    0.73
     grey
    0.72
    brad
    0.72
    DYNAMIC
    0.72
    清水
    0.71
     onlyOwner
    0.71
    Activations Density 0.030%

    No Known Activations