© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12532
    Prev
    Next
    INDEX
    Explanations

    Select one:

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

    This neuron is sensitive to document‐structure or formatting markers—e.g. isolated punctuation or symbol tokens (###, ellipses, standalone line breaks) used as headings, separators, or section markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MATH
    0.57
     wavefunction
    0.57
    <b>
    0.57
    ¢
    0.55
     >
    0.54
    obucket
    0.54
     algebraically
    0.53
     waterline
    0.53
     /(
    0.52
     wavelength
    0.52
    POSITIVE LOGITS
    Explanation
    0.73
    解释
    0.63
     объяснить
    0.63
    explanation
    0.62
     explanation
    0.62
    解釋
    0.62
     açıkl
    0.61
     информа
    0.61
     penjelasan
    0.59
    ās
    0.59
    Activations Density 0.003%

    No Known Activations