© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5111
    Prev
    Next
    INDEX
    Explanations

    examining or exploring content

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

    The neuron detects unusually rare or content-heavy tokens—particularly low-frequency words and names.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    atributo
    0.73
     αυτό
    0.71
     замет
    0.70
     ช่วง
    0.70
     zerstört
    0.68
    chette
    0.67
     преди
    0.66
     слегка
    0.66
     zusammen
    0.66
     проис
    0.65
    POSITIVE LOGITS
     Visions
    0.78
    examine
    0.78
    explore
    0.74
    جيل
    0.74
     OT
    0.73
    怙
    0.71
    Nub
    0.71
    tickets
    0.71
    suk
    0.71
    ྦ
    0.70
    Activations Density 0.000%

    No Known Activations