© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102993
    Prev
    Next
    INDEX
    Explanations

    leaf, vane, blades

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

    words related to mechanical components in engineering, particularly parts of turbines, valves, and mechanical systems like vanes, leaves, and shutters.

    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
     documenti
    -1.40
    👧
    -1.32
     cebola
    -1.30
    Hechos
    -1.30
    他们的
    -1.29
    鈈
    -1.28
     intention
    -1.28
    lysm
    -1.26
    OPPO
    -1.25
     zile
    -1.24
    POSITIVE LOGITS
    '
    1.46
    .)
    1.45
     nettement
    1.42
     which
    1.41
    </h5>
    1.34
     które
    1.34
     where
    1.30
    .'
    1.29
     distintas
    1.29
     completamente
    1.28
    Activations Density 0.067%

    No Known Activations