© 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. 10-GEMMASCOPE-RES-131K
    7. 13441
    Prev
    Next
    INDEX
    Explanations

    Real Ya-Ya

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

    The neuron is primarily triggered by numeric literals (especially floating‐point numbers) in code or markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Another
    -1.84
     It
    -1.63
    <td>
    -1.56
     Again
    -1.56
     When
    -1.55
    Appellee
    -1.51
     \
    -1.48
     and
    -1.48
    着头
    -1.45
     A
    -1.45
    POSITIVE LOGITS
     kristal
    1.89
    鷽
    1.86
     maske
    1.72
    んだから
    1.69
     seks
    1.68
     kupa
    1.67
     ペア
    1.64
     kablo
    1.62
     saks
    1.61
     hatta
    1.59
    Activations Density 0.000%

    No Known Activations