© 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. 36000
    Prev
    Next
    INDEX
    Explanations

    ACB arrests

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

    The neuron is especially sensitive to numeric tokens—dates, distances, measurements, and other numbers.

    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
    Чем
    -1.14
    био
    -1.11
    אַ
    -1.09
    lève
    -1.05
     кроссовки
    -1.04
     المقال
    -1.03
    rüstung
    -0.98
    עוד
    -0.95
    ༘
    -0.95
    ÇÃO
    -0.94
    POSITIVE LOGITS
     aço
    1.20
     about
    1.14
     especially
    1.11
     instead
    1.09
     uſ
    1.07
     noved
    1.06
     there
    1.05
     specially
    1.04
     such
    1.03
     people
    1.02
    Activations Density 0.033%

    No Known Activations