© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65894
    Prev
    Next
    INDEX
    Explanations

    bird wing anatomy

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

    references to aircraft wings or wing-related structural components.

    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
     you
    -3.17
    zelfde
    -2.94
    .
    -2.69
    縂
    -2.64
    瓩
    -2.48
    -“
    -2.47
    魨
    -2.41
    gucig
    -2.41
    ”
    -2.39
    “
    -2.34
    POSITIVE LOGITS
     für
    2.95
     For
    2.80
     intrepid
    2.66
     Для
    2.64
     για
    2.56
     You
    2.55
     với
    2.47
    m
    2.47
    い
    2.42
     '
    2.39
    Activations Density 0.007%

    No Known Activations