© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8574
    Prev
    Next
    INDEX
    Explanations

    code module imports

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

    The neuron is keyed to technical code terms—names of programming libraries, frameworks, classes, and related identifiers.

    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_24_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
     വരുന്ന
    0.57
    itié
    0.53
    َص
    0.50
    ارع
    0.47
    ifferentiating
    0.46
     ОТ
    0.46
    сок
    0.46
    četně
    0.46
    enteuer
    0.46
     Université
    0.46
    POSITIVE LOGITS
     lemmas
    0.44
    的使用
    0.42
     conventions
    0.42
     crítico
    0.39
     hut
    0.38
    .
    0.38
     techniques
    0.37
     Ltd
    0.37
     Wrigley
    0.37
     idiot
    0.37
    Activations Density 0.056%

    No Known Activations