© 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. 40465
    Prev
    Next
    INDEX
    Explanations

    names and biological terms

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

    This neuron detects mentions of "gill" or "gills" related to fish anatomy or person's surname.

    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
    al
    -3.36
    an
    -2.88
     instill
    -2.66
    呖
    -2.61
     strive
    -2.56
    èlement
    -2.42
    旸
    -2.38
    lccn
    -2.36
     delineate
    -2.36
     obstruct
    -2.33
    POSITIVE LOGITS
    2
    2.81
    5
    2.72
    是
    2.69
    1
    2.56
    8
    2.56
    );
    2.38
     termed
    2.27
    9
    2.22
    [
    2.20
     Your
    2.19
    Activations Density 0.004%

    No Known Activations