© 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. 109786
    Prev
    Next
    INDEX
    Explanations

    look back, exchanged words, get today

    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
    Paperback
    -0.82
     eisen
    -0.81
     leiden
    -0.80
    ゼット
    -0.78
    自身的
    -0.77
     Felicia
    -0.75
     flott
    -0.75
    gezogen
    -0.75
    architect
    -0.74
    преки
    -0.74
    POSITIVE LOGITS
     logic
    0.92
     rub
    0.89
     sarcastic
    0.87
    llac
    0.87
     crux
    0.83
    Cor
    0.82
     poignant
    0.82
    Sam
    0.80
    Sal
    0.79
    enz
    0.78
    Activations Density 0.009%

    No Known Activations