© 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. 34346
    Prev
    Next
    INDEX
    Explanations

    legal proceedings, arrests, named people and places

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

    This neuron activates on numeric tokens, especially numbers and decimal values.

    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
     certain
    -1.25
    ліз
    -1.21
     kakao
    -1.20
    nější
    -1.18
     violación
    -1.13
     altes
    -1.09
     február
    -1.07
     noël
    -1.07
     accompagné
    -1.06
     such
    -1.05
    POSITIVE LOGITS
    ถ้า
    1.36
     الشرطة
    1.14
     McLaugh
    1.13
    เคย
    1.13
     демон
    1.10
    通貨
    1.10
     домаш
    1.09
    olare
    1.09
    熾
    1.06
    定番
    1.04
    Activations Density 0.019%

    No Known Activations