© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59377
    Prev
    Next
    INDEX
    Explanations

    and followed by non-alphanumeric characters

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

    The neuron activates on numeric values (digits or numeric constants) appearing in mathematical 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_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
     שלהם
    -1.66
    Quantidade
    -1.65
    ITIONS
    -1.61
    Tecnologia
    -1.60
    万能
    -1.59
     is
    -1.56
     sogenannten
    -1.55
     rằng
    -1.55
    ですが
    -1.54
    Objetivos
    -1.52
    POSITIVE LOGITS
    الحياه
    2.02
    釤
    1.89
     the
    1.88
     that
    1.75
     to
    1.66
     bụ
    1.63
    \
    1.55
    䜣
    1.54
    
    1.54
    熥
    1.53
    Activations Density 0.052%

    No Known Activations