© 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. 34-GEMMASCOPE-RES-131K
    7. 76145
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron is tuned to detect numeric literals (sequences of digits) in code or 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_34/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
    Champaign
    -0.69
    byteArray
    -0.67
    jenis
    -0.67
     medulla
    -0.66
     Kassel
    -0.66
     положи
    -0.65
     inventory
    -0.65
     tipo
    -0.64
    Prefer
    -0.64
     pozy
    -0.63
    POSITIVE LOGITS
    Germania
    0.71
     Ahl
    0.66
    dentist
    0.65
    hskip
    0.65
    艿
    0.63
    bardier
    0.62
    איך
    0.62
     McDaniel
    0.62
     Devi
    0.61
    Благо
    0.60
    Activations Density 0.063%

    No Known Activations