© 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. 34-GEMMASCOPE-RES-131K
    7. 1457
    Prev
    Next
    INDEX
    Explanations

    LaTeX math symbols and macros

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

    This neuron detects numeric labels used in document markup—e.g. line numbers or diff-hunk markers (numbers following backslashes like “\1312” or in “@@ 964”).

    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
     prevent
    -0.81
    ді
    -0.77
    ılan
    -0.73
    ทะ
    -0.73
    炉
    -0.70
    ƛ
    -0.69
    parseDouble
    -0.68
     enables
    -0.67
     сливо
    -0.67
    クー
    -0.67
    POSITIVE LOGITS
    ↵
    1.27
    וקה
    0.90
     Tagore
    0.86
     infuri
    0.84
    ASR
    0.83
    ländische
    0.81
    SOLID
    0.79
    0.79
     scythe
    0.79
    ?")
    0.77
    Activations Density 0.021%
    No Known Activations