© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14404
    Prev
    Next
    INDEX
    Explanations

    birthday

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

    This neuron strongly activates on the final content word just before a sentence boundary.

    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
     woe
    0.90
     Illumina
    0.90
     maíz
    0.89
     ئەو
    0.88
     Vegeta
    0.86
    ש
    0.86
     Química
    0.83
     foolproof
    0.82
     pectin
    0.82
     Whey
    0.82
    POSITIVE LOGITS
     වශයෙන්
    0.87
    خرى
    0.86
    الم
    0.85
    А
    0.80
    épend
    0.80
    الش
    0.80
    ો
    0.79
     આગળ
    0.79
    ક્ષા
    0.78
    ين
    0.77
    Activations Density 0.000%

    No Known Activations