© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5014
    Prev
    Next
    INDEX
    Explanations

    code blocks and technical terms

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

    This neuron fires on words immediately surrounding explicit numeric or measurement contexts (e.g. “for” before a number, “price” after a number, or other terms appearing right next to figures).

    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
    rews
    0.78
    oxing
    0.78
     sidelines
    0.77
     Natives
    0.77
    s
    0.77
    ità
    0.76
     आम्हाला
    0.75
    app
    0.75
     nostri
    0.75
    ನ
    0.75
    POSITIVE LOGITS
    ঘ্রই
    0.94
     وبعد
    0.88
    Toplam
    0.85
     Вы
    0.81
     ضمان
    0.78
     المقدم
    0.76
     sehe
    0.75
    取引
    0.74
     Aseg
    0.73
     Pilar
    0.72
    Activations Density 0.000%

    No Known Activations