© 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. 22-GEMMASCOPE-RES-131K
    7. 72039
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    technical terminology in scientific, medical, and programming contexts.

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

    The neuron strongly activates on numeric tokens (e.g. integers or decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kjer
    -1.02
    QSize
    -0.93
     vedno
    -0.88
    过来的
    -0.88
    -0.86
     壓
    -0.85
     synes
    -0.84
    Aceite
    -0.84
    chengladbach
    -0.83
    來的
    -0.83
    POSITIVE LOGITS
     Reſ
    1.32
     utilisant
    1.16
     contenedor
    1.13
     فقال
    1.08
    ౬
    1.07
    vermectin
    1.06
     vérifier
    1.05
    摀
    1.03
     ſte
    1.03
    uſe
    1.02
    Activations Density 0.130%

    No Known Activations