© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118138
    Prev
    Next
    INDEX
    Explanations

    peace and lines

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

    The neuron fires on long digit sequences—especially four-digit numbers—such as those used in line-number or page-number references.

    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
    نحوه
    -0.83
    क्षा
    -0.80
    ›
    -0.77
    DCC
    -0.76
    SPECIFICATIONS
    -0.75
     mmHg
    -0.74
     Mathematik
    -0.74
    cribir
    -0.73
    Manifest
    -0.72
    mmung
    -0.72
    POSITIVE LOGITS
     of
    1.62
    Of
    1.16
    of
    1.12
     Of
    1.03
     ऑफ
    0.79
     OF
    0.75
    OF
    0.75
    ของ
    0.71
    ของคุณ
    0.70
    tosí
    0.70
    Activations Density 0.049%

    No Known Activations