© 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. 110618
    Prev
    Next
    INDEX
    Explanations

    tuber calcanei, vermiculations, born, shaped

    np_acts-logits-general · gemini-2.5-flash-lite

    anatomical structures and physical protrusions in medical and scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     budowy
    -0.77
    學院
    -0.77
     recite
    -0.75
     iniciativa
    -0.72
     rijden
    -0.70
    澜
    -0.69
     hlavně
    -0.69
     edificio
    -0.68
     condena
    -0.68
    梔
    -0.68
    POSITIVE LOGITS
    ի
    0.87
    rouw
    0.79
    ITIES
    0.78
    Visibility
    0.77
     הת
    0.76
    <0xA8>
    0.76
     {.
    0.75
    新
    0.75
    ganie
    0.75
    ዜ
    0.75
    Activations Density 0.025%

    No Known Activations