© 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. 34-GEMMASCOPE-RES-131K
    7. 107164
    Prev
    Next
    INDEX
    Explanations

    GGRESCAN, Cotton functional genomics

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

    dates, version numbers, and formatting in technical documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects standalone numeric tokens (i.e. numbers or year/version digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Kaplan
    -0.75
    PageIndex
    -0.72
     Hage
    -0.71
     Madam
    -0.68
    ߝ
    -0.66
     BAC
    -0.65
    ிக்
    -0.65
     free
    -0.65
    BAC
    -0.65
    าด
    -0.64
    POSITIVE LOGITS
    ppes
    0.75
    MAINTENANCE
    0.71
    Off
    0.71
     Govt
    0.70
     bearing
    0.70
     porte
    0.67
     кү
    0.65
     ziet
    0.64
     Horseshoe
    0.64
    насти
    0.63
    Activations Density 0.060%

    No Known Activations