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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118851
    Prev
    Next
    INDEX
    Explanations

    transient outward K+ current

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

    This neuron detects numerical methods and mathematical algorithms, particularly related to differential equations and computational mathematics.

    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_34/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
    ANCING
    -0.79
    сної
    -0.78
     afar
    -0.75
    tov
    -0.74
     المث
    -0.73
     sejumlah
    -0.73
    plink
    -0.71
    Grady
    -0.71
    HasColumn
    -0.71
     pome
    -0.71
    POSITIVE LOGITS
     Butcher
    1.08
     Fame
    0.75
    btnut
    0.73
    Discus
    0.73
     manteiga
    0.73
     szól
    0.71
    ंदु
    0.69
    springboot
    0.68
    ğini
    0.68
     Tableau
    0.67
    Activations Density 0.033%

    No Known Activations