© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78093
    Prev
    Next
    INDEX
    Explanations

    vocal fold adduction

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

    The neuron strongly activates on tokens containing digits (e.g. numbers, years, numeric sequences, and numeric punctuation).

    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
    <tbody>
    -0.93
     www
    -0.84
    <!--<
    -0.82
    <blockquote>
    -0.78
    Jegyzetek
    -0.77
    >=</
    -0.76
    ⅽ
    -0.75
     וְ
    -0.75
    Bey
    -0.74
    exam
    -0.74
    POSITIVE LOGITS
    accro
    0.90
    praia
    0.88
     सेवा
    0.87
     könnte
    0.84
    élimin
    0.83
    🡪
    0.79
    複雑
    0.79
    竽
    0.79
     nordrhein
    0.79
    quirer
    0.78
    Activations Density 0.001%

    No Known Activations