© 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. 72786
    Prev
    Next
    INDEX
    Explanations

    medical conditions and code references

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

    numerical values and data in technical or scientific text.

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

    The neuron fires on numeric tokens (measurements, counts, and other numbers) in technical or scientific 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
    ⻑
    -1.14
    OGRAPH
    -1.01
    Serves
    -0.98
    一听
    -0.96
    װ
    -0.96
     user
    -0.95
    おすすめです
    -0.94
    usschuss
    -0.94
     għall
    -0.94
    Уважаемые
    -0.92
    POSITIVE LOGITS
     tatou
    1.16
     triom
    1.10
     drame
    1.10
     sembla
    1.07
     ritrov
    1.05
     chô
    1.03
     menac
    1.02
     giebt
    1.01
     envelo
    1.00
     verbe
    0.99
    Activations Density 0.177%

    No Known Activations