© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10731
    Prev
    Next
    INDEX
    Explanations

    installing libraries and classes

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

    The neuron detects lines of formal bibliographic citations or reference‐style entries (e.g. journal names, volumes, years, page numbers).

    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_24_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
    ра
    1.01
    на
    0.90
    н
    0.89
    न
    0.86
    ₱
    0.83
    ל
    0.82
     ಇತರ
    0.82
    와의
    0.82
    Н
    0.81
    sub
    0.80
    POSITIVE LOGITS
    érios
    0.84
     보인다
    0.84
    üyor
    0.75
     Hö
    0.75
    的热
    0.74
     مظ
    0.73
     झग
    0.73
    に行
    0.72
     jū
    0.72
     Gä
    0.71
    Activations Density 0.000%

    No Known Activations