© 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. 118835
    Prev
    Next
    INDEX
    Explanations

    tail and fin anatomy

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

    descriptions of technical parts or features of objects, particularly in aviation, marine biology, and engineering documents.

    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
    ılması
    -0.83
    兖
    -0.80
    ⚀
    -0.76
     possuem
    -0.74
    綬
    -0.74
     tecnológica
    -0.71
    からも
    -0.71
    ůže
    -0.70
    Wc
    -0.70
    cessite
    -0.69
    POSITIVE LOGITS
     tail
    2.67
     fins
    2.50
    tail
    2.03
     fin
    2.02
     tails
    1.93
     Tail
    1.93
    Tail
    1.86
    尾
    1.82
    fins
    1.70
    tails
    1.65
    Activations Density 0.053%

    No Known Activations