© 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. 129069
    Prev
    Next
    INDEX
    Explanations

    hyperbolic geometry or anabolic steroids

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

    This neuron detects mathematical and scientific terms related to hyperbolic geometry and anabolic steroids.

    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
    𞤢
    -2.64
    INTRODUCCIÓN
    -2.27
    Beskrivelse
    -2.22
    Pengertian
    -2.19
    をし
    -2.14
    which
    -2.14
    SÍ
    -2.14
    
    -2.14
    felpa
    -2.13
    DÉ
    -2.11
    POSITIVE LOGITS
    s
    3.05
    $
    2.58
     \
    2.47
     {
    2.25
    呖
    2.05
    <blockquote>
    2.00
     мальчик
    1.95
     другого
    1.88
    ti
    1.85
    पुर
    1.85
    Activations Density 0.005%

    No Known Activations