© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37785
    Prev
    Next
    INDEX
    Explanations

    specifications and numbers

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

    The neuron mainly picks out numeric tokens, especially digits in legal citations or case/document numbers.

    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
    👩
    -0.70
    onema
    -0.69
    gallery
    -0.69
     Newtonsoft
    -0.69
    vær
    -0.69
     områ
    -0.68
    nical
    -0.67
    ındaki
    -0.67
    اية
    -0.66
    探し
    -0.66
    POSITIVE LOGITS
    Races
    0.74
     gelişti
    0.73
    گز
    0.72
     derby
    0.72
    ふ
    0.71
     değişti
    0.71
    Surprised
    0.71
    Drunk
    0.70
    教材
    0.70
     macrophages
    0.70
    Activations Density 0.015%

    No Known Activations