© 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. 14305
    Prev
    Next
    INDEX
    Explanations

    lists of items

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

    The neuron tends to light up on relatively uncommon, content‐bearing words (i.e. high–tf-idf terms) rather than on frequent function words.

    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
     и
    0.76
     and
    0.74
     idealistic
    0.70
     và
    0.69
     а
    0.69
     "
    0.68
     externe
    0.67
     academic
    0.65
     &
    0.64
     elit
    0.64
    POSITIVE LOGITS
    沙发
    0.86
    一带
    0.82
     korero
    0.77
    ウンド
    0.75
    lewati
    0.75
    你需要
    0.75
    માં
    0.74
    같은
    0.74
    Roasted
    0.73
    的名字
    0.73
    Activations Density 0.000%

    No Known Activations