© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110500
    Prev
    Next
    INDEX
    Explanations

    version or description context

    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
    ulations
    -0.80
    ea
    -0.79
    çait
    -0.79
    Ͱ
    -0.78
    uous
    -0.78
     `;
    -0.78
     bautizo
    -0.78
    InitStruct
    -0.77
    塬
    -0.77
     млрд
    -0.77
    POSITIVE LOGITS
     atti
    0.82
    getAttribute
    0.81
     الی
    0.79
    mousemove
    0.77
     comporta
    0.74
    SuppressMessage
    0.74
     aynı
    0.73
    疲
    0.72
    kura
    0.72
    版本
    0.72
    Activations Density 0.003%

    No Known Activations