© 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. 11843
    Prev
    Next
    INDEX
    Explanations

    editing commands

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

    The neuron is a “long‐token detector,” firing strongly on unusually long tokens (e.g. lengthy words or multi‐digit numeric strings).

    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
    هد
    0.80
    #![
    0.72
     هز
    0.71
     menunggu
    0.69
     abb
    0.68
    واه
    0.68
    -
    0.67
     moo
    0.66
     グラ
    0.66
     واب
    0.65
    POSITIVE LOGITS
    тся
    0.91
    ো
    0.84
    ोला
    0.80
    isr
    0.80
    reversed
    0.79
    adays
    0.79
    contrar
    0.79
    earnings
    0.79
    ET
    0.78
    ியில்
    0.78
    Activations Density 0.000%

    No Known Activations