© 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. 11320
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron fires strongly on low‐frequency or highly specific tokens—proper names, numbers, model identifiers, and other rare/unique words.

    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
    젹
    0.84
    ış
    0.76
    किस
    0.75
    owel
    0.72
    oka
    0.71
    azed
    0.69
     =\
    0.69
    olojik
    0.68
    lek
    0.67
    hese
    0.66
    POSITIVE LOGITS
     ABO
    0.92
     beatae
    0.88
    י
    0.81
     Merton
    0.78
    теро
    0.77
     bijoux
    0.75
     Angola
    0.74
     vacío
    0.74
     Rhino
    0.74
     biot
    0.74
    Activations Density 0.001%

    No Known Activations