© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97971
    Prev
    Next
    INDEX
    Explanations

    angular framework code

    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
    NameExpr
    -0.95
    icona
    -0.80
    DataBinding
    -0.78
    身形
    -0.77
    '||
    -0.76
    谤
    -0.74
    enovo
    -0.72
     polegadas
    -0.71
    ində
    -0.71
    cucina
    -0.70
    POSITIVE LOGITS
     environment
    1.14
    環境
    1.05
    environment
    1.04
    environments
    0.91
     environments
    0.86
     service
    0.85
     modal
    0.84
     Environment
    0.83
    Environment
    0.82
    Cookies
    0.81
    Activations Density 0.023%

    No Known Activations