© 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. 4236
    Prev
    Next
    INDEX
    Explanations

    list separators

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

    This neuron activates strongly on comma punctuation separators.

    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
    υτό
    0.59
    aujourd
    0.54
    क्ष्म
    0.53
    ূন্য
    0.52
    ধরনের
    0.50
    ل
    0.50
     ล่ะ
    0.50
     इट्स
    0.49
    lių
    0.49
    嘅
    0.49
    POSITIVE LOGITS
     and
    1.14
     which
    0.98
     but
    0.96
     whereupon
    0.88
     এবং
    0.87
    以及
    0.83
     sodass
    0.83
     as
    0.82
     ਅਤੇ
    0.82
     valamint
    0.82
    Activations Density 0.523%

    No Known Activations