© 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. 38371
    Prev
    Next
    INDEX
    Explanations

    names and numbers

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

    The neuron primarily detects sequences of digits (numeric characters).

    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
    ėje
    -0.96
    は
    -0.96
    で
    -0.93
     syk
    -0.91
     toughest
    -0.91
     подру
    -0.89
    があり
    -0.88
    狛
    -0.87
     både
    -0.86
    áž
    -0.86
    POSITIVE LOGITS
     such
    1.13
    為に
    1.05
    頜
    1.02
    ᱼ
    1.02
    でしたか
    1.00
    ְב
    0.94
     рекомендую
    0.94
    Acesso
    0.93
    ｀
    0.93
    的問題
    0.92
    Activations Density 0.000%

    No Known Activations