© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10013
    Prev
    Next
    INDEX
    Explanations

    technical terms and foreign words

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

    The neuron is picking out title‐style or heading keywords—i.e. capitalized, significant words used in section titles, headlines, or labels.

    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_31_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
     โปร
    0.39
     Кі
    0.39
    Ava
    0.38
    صة
    0.38
    ൯
    0.38
    Ін
    0.38
     เสร็จ
    0.37
     hoàn
    0.37
    {}'.
    0.37
    ೂರ್ವ
    0.37
    POSITIVE LOGITS
     arrhyth
    0.36
     MSRP
    0.36
     Lightroom
    0.35
     viscoelastic
    0.34
     WARRANTIES
    0.34
     epileptic
    0.34
     birefringence
    0.33
     irradiance
    0.33
     கட்டுமான
    0.33
     ayatan
    0.33
    Activations Density 0.075%

    No Known Activations