© 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. 22-GEMMASCOPE-RES-131K
    4. 35947
    Prev
    Next
    INDEX
    Explanations

    programming and software development contexts

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

    The neuron activates on numeric tokens (integers, floating-point numbers, version numbers, etc.) in the 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_22/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
     in
    -1.01
     of
    -0.98
     at
    -0.97
     ویتامین
    -0.96
     лимон
    -0.95
    sieke
    -0.94
    Nép
    -0.92
    riebenen
    -0.92
    sqcup
    -0.92
     because
    -0.91
    POSITIVE LOGITS
    艏
    1.08
    Init
    1.00
     фаса
    0.96
     préparer
    0.94
     décider
    0.93
    מעות
    0.93
    "><
    0.91
    Control
    0.90
     sillas
    0.89
     situation
    0.88
    Activations Density 0.004%

    No Known Activations