© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4767
    Prev
    Next
    INDEX
    Explanations

    languages, punctuation, or numbers

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

    The neuron strongly activates on tokens drawn from academic citation metadata—especially volume‐, issue‐, and page‐number tokens in reference lists.

    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
    ('/')
    0.71
    cha
    0.67
     विस्तृत
    0.67
    ため
    0.66
    ("/")
    0.66
    zer
    0.66
    brid
    0.64
    ché
    0.63
    zungen
    0.63
    scribed
    0.63
    POSITIVE LOGITS
    ه
    0.85
     adesso
    0.78
     réforme
    0.73
     biologie
    0.73
    ਉ
    0.73
    अब
    0.72
     trekk
    0.72
     problèmes
    0.71
     quedó
    0.71
     ajout
    0.71
    Activations Density 0.000%

    No Known Activations