© 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. 34-GEMMASCOPE-RES-131K
    7. 31057
    Prev
    Next
    INDEX
    Explanations

    character and regular expression patterns

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

    The neuron detects the three‐character pattern of a regex character‐range (e.g. “a–z” or “A–Z”).

    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
    힝
    -1.50
    ゔ
    -1.04
    امد
    -0.85
    もあって
    -0.82
    ポイントは
    -0.79
    ازم
    -0.78
     alis
    -0.77
     Nicolae
    -0.77
    berkeley
    -0.75
    circ
    -0.73
    POSITIVE LOGITS
    Z
    1.37
     Z
    1.30
     z
    1.19
    z
    1.14
    zA
    0.91
    Za
    0.88
    為に
    0.88
     zaby
    0.86
     geschehen
    0.86
    わけです
    0.84
    Activations Density 0.008%

    No Known Activations