© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11996
    Prev
    Next
    INDEX
    Explanations

    desensitization, frecuentemente, Rasi

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

    The neuron is acting as a citation/bibliography detector: it spikes on tokens that appear in reference entries (author names or journal‐style abbreviations, volume/page markers, etc.).

    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
     மற்றும்
    0.13
    <unused2188>
    0.12
    債
    0.11
     ซึ่ง
    0.11
     ಮತ್ತು
    0.11
    as
    0.11
    which
    0.11
     ignoreString
    0.11
    <0x80>
    0.11
     کنند
    0.11
    POSITIVE LOGITS
     Roundup
    0.13
     Middlesbrough
    0.13
    REW
    0.13
     c
    0.12
     EB
    0.12
    TT
    0.12
     fift
    0.12
    ध्ये
    0.12
     Haunted
    0.11
     NRA
    0.11
    Activations Density 0.002%

    No Known Activations