© 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. 12471
    Prev
    Next
    INDEX
    Explanations

    index mid

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

    The neuron detects numeric components of academic references—especially volumes, issue/page numbers, and their separators.

    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
    ((-
    0.61
    Subtract
    0.59
    subtract
    0.58
    ющиеся
    0.58
    residuals
    0.58
     subtracting
    0.57
    hybrid
    0.57
    ющийся
    0.55
    ROff
    0.55
    *((
    0.54
    POSITIVE LOGITS
     nächste
    0.63
     nächsten
    0.63
    下一个
    0.61
    次
    0.61
     suces
    0.60
    下一
    0.59
    次の
    0.59
     преда
    0.55
     ಆತ್ಮ
    0.54
     next
    0.53
    Activations Density 0.068%

    No Known Activations