© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127815
    Prev
    Next
    INDEX
    Explanations

    parts of trees

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

    references to leaves, particularly in nature contexts like trees, branches, and autumn.

    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_10/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
     גם
    -1.63
    冷蔵庫
    -1.61
     también
    -1.48
     Comuni
    -1.41
     sendiri
    -1.41
     également
    -1.41
     garagem
    -1.38
    躋
    -1.35
     manuelle
    -1.34
     Bedür
    -1.31
    POSITIVE LOGITS
    各大
    1.59
     other
    1.53
     causando
    1.38
     ว่า
    1.35
     Specifically
    1.34
     Our
    1.30
    ullable
    1.30
     acquire
    1.30
     bahawa
    1.30
    </em>
    1.28
    Activations Density 0.017%

    No Known Activations