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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70925
    Prev
    Next
    INDEX
    Explanations

    such as and United Kingdom

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

    The neuron activates on numeric tokens—section or reference numbers, percentages, and other numerical citations—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
     of
    -1.18
     veröffentlich
    -0.93
     sedang
    -0.92
    conos
    -0.92
     to
    -0.91
     by
    -0.91
     считается
    -0.88
    missao
    -0.88
    ordat
    -0.87
    江南
    -0.87
    POSITIVE LOGITS
     egreg
    1.20
     exhib
    1.16
    麻煩
    1.12
     följande
    1.11
     segíts
    1.10
     jajaja
    1.09
    ærer
    1.06
     szinte
    1.06
     suh
    1.06
     tems
    1.05
    Activations Density 0.093%

    No Known Activations