© 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. 65147
    Prev
    Next
    INDEX
    Explanations

    limit or integral notation

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

    The neuron detects LaTeX‐style mathematical notation tokens (e.g. commands like “\delta,” “\int,” “\lim,” “\frac,” etc.).

    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
    atius
    -0.82
    gom
    -0.75
     bisherigen
    -0.74
    Сколько
    -0.74
     too
    -0.73
     医院
    -0.72
     使い方
    -0.71
     אף
    -0.70
     显示
    -0.69
    więcej
    -0.69
    POSITIVE LOGITS
     among
    0.91
    government
    0.75
    
    0.74
     gouvernement
    0.74
    haber
    0.73
    velocityY
    0.73
    нциклопе
    0.72
    Talent
    0.72
    _{\
    0.71
     bedeckt
    0.71
    Activations Density 0.023%

    No Known Activations