© 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. 84096
    Prev
    Next
    INDEX
    Explanations

    citations with numbers

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

    The neuron mainly detects numeric tokens or sequences of digits (e.g., page numbers, years, or reference indices).

    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
     only
    -1.04
     even
    -0.90
     now
    -0.90
    meetings
    -0.87
    ℠
    -0.83
    protein
    -0.81
    主任
    -0.81
    issons
    -0.80
    ｅ
    -0.80
     mainly
    -0.80
    POSITIVE LOGITS
    riae
    0.93
     troisième
    0.89
     soluciones
    0.88
    mbolo
    0.87
    ramanian
    0.84
    vedo
    0.83
    我が家の
    0.82
    tacles
    0.82
    лактика
    0.82
     një
    0.82
    Activations Density 0.002%

    No Known Activations