© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112223
    Prev
    Next
    INDEX
    Explanations

    lists of numbers

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

    The neuron strongly activates on the standalone numeral “2” in code or data, i.e. it is detecting occurrences of the number two.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     I
    -1.91
    ing
    -1.84
     
    -1.62
    ionales
    -1.58
    haps
    -1.57
    (
    -1.56
    all
    -1.56
    tion
    -1.55
    t
    -1.52
    ue
    -1.45
    POSITIVE LOGITS
     solucionar
    1.46
    ФО
    1.41
    棪
    1.38
    כמה
    1.36
    這是
    1.34
    איך
    1.33
     艺术
    1.31
    אם
    1.30
    ｫ
    1.29
    憮
    1.29
    Activations Density 0.042%

    No Known Activations