© 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. 15932
    Prev
    Next
    INDEX
    Explanations

    predictor of a

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

    The neuron strongly flags words that appear as the very first token of a new text segment.

    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
     פ
    0.79
    よく
    0.73
    ه
    0.72
     ਤ
    0.71
     ו
    0.71
    фи
    0.70
    ।”
    0.69
    ा
    0.69
    を発
    0.68
     প্রতিযোগিতা
    0.68
    POSITIVE LOGITS
    örungen
    0.81
    უშ
    0.81
     swabs
    0.80
     compute
    0.80
    nl
    0.79
     Heidelberg
    0.78
     Wouldn
    0.78
     observance
    0.78
     outcrops
    0.78
     kerak
    0.77
    Activations Density 0.000%

    No Known Activations