© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6284
    Prev
    Next
    INDEX
    Explanations

    Project setup

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

    The main thing this neuron does is pick out content‐bearing words (i.e. non-stopwords like nouns and adjectives) as opposed to common 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
    i
    1.08
    c
    0.99
    j
    0.95
    de
    0.95
    sys
    0.93
    n
    0.89
    d
    0.85
    jq
    0.84
    f
    0.84
    sn
    0.83
    POSITIVE LOGITS
    ร่างกาย
    0.91
    ське
    0.84
     아무
    0.83
     कोई
    0.82
    нг
    0.82
     поді
    0.82
     کوئی
    0.81
     આવી
    0.78
     endothelial
    0.78
    自分で
    0.77
    Activations Density 0.002%

    No Known Activations