© 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. 11272
    Prev
    Next
    INDEX
    Explanations

    how are you

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

    The neuron strongly activates on Arabic‐script text, effectively identifying segments written in Arabic.

    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
     -
    1.10
     is
    0.97
    ,
    0.97
    ↵↵
    0.96
     (
    0.95
     $\
    0.88
     for
    0.87
     can
    0.85
    ↵↵↵
    0.84
     in
    0.82
    POSITIVE LOGITS
    نا
    1.28
    كم
    1.24
    ث
    1.20
    ًا
    1.20
    ِي
    1.18
    ين
    1.16
    ية
    1.16
     وم
    1.13
    ى
    1.13
    َ
    1.13
    Activations Density 0.006%

    No Known Activations