© 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. 22-GEMMASCOPE-RES-131K
    7. 71879
    Prev
    Next
    INDEX
    Explanations

    rounding numbers or specifying quantities

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

    The neuron is specifically picking out occurrences of the digit “0” (especially when it appears in long numeric strings).

    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
    赑
    -2.67
    おわりに
    -2.42
    うわ
    -2.36
    もうすぐ
    -2.34
    明日は
    -2.25
    
    -2.23
    棡
    -2.22
    ௅
    -2.20
    𓆉
    -2.19
    に来て
    -2.14
    POSITIVE LOGITS
     to
    2.23
    an
    2.14
    0
    2.09
    a
    2.03
     of
    1.99
    ”
    1.98
     подготовка
    1.96
     (
    1.91
     You
    1.81
    в
    1.80
    Activations Density 0.022%

    No Known Activations