© 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. 34-GEMMASCOPE-RES-131K
    7. 64626
    Prev
    Next
    INDEX
    Explanations

    parentheses after numbers

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

    This neuron detects numeric literals—especially digits appearing in comma‐separated sequences inside parentheses (e.g. tensor or array shape specs).

    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
     bisous
    -0.86
     probably
    -0.85
     possibly
    -0.83
    addFlags
    -0.82
    <0xD2>
    -0.81
     problemu
    -0.80
     tantos
    -0.79
     likely
    -0.78
    elfs
    -0.78
     skru
    -0.77
    POSITIVE LOGITS
    রণ
    0.85
    理会
    0.81
    apore
    0.81
     zweimal
    0.79
    יקה
    0.79
     разных
    0.77
    bern
    0.76
    
    0.76
     wacky
    0.75
     разные
    0.75
    Activations Density 0.019%

    No Known Activations