© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7129
    Prev
    Next
    INDEX
    Explanations

    after each iteration / step / pass

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

    That neuron fires strongly on occurrences of the phrase “end of” in text.

    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
     extrêmement
    0.65
    sstream
    0.61
     estremamente
    0.61
     परिस्थितियों
    0.60
    eltat
    0.60
    UUID
    0.59
    変化
    0.59
    下げ
    0.59
    āo
    0.59
     بالکل
    0.58
    POSITIVE LOGITS
    lukan
    0.71
     recientes
    0.70
    ஜெ
    0.70
     mấy
    0.69
     bloody
    0.68
     TEL
    0.68
    ..?
    0.67
    ?[
    0.66
    済み
    0.66
     kiosks
    0.65
    Activations Density 0.001%

    No Known Activations