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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7712
    Prev
    Next
    INDEX
    Explanations

    categories and No

    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
    机
    -0.70
    Groundwater
    -0.69
    Initi
    -0.69
     общий
    -0.66
     Reeves
    -0.63
    ExecutionContext
    -0.63
    嶋
    -0.63
     investissement
    -0.63
    جمع
    -0.62
     Ayurvedic
    -0.62
    POSITIVE LOGITS
     commanding
    0.69
     Rok
    0.68
    Minha
    0.67
     violent
    0.67
     undetected
    0.66
    unding
    0.65
    ukset
    0.64
    fromUtf
    0.64
     плохо
    0.63
     quebra
    0.63
    Activations Density 0.092%

    No Known Activations