© 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. 6519
    Prev
    Next
    INDEX
    Explanations

    units and formulas

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

    The neuron strongly activates on longer, content‐bearing words (i.e. multi‐syllable or “long” tokens), as opposed to short function words or punctuation.

    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
     특히
    0.98
     మీరు
    0.85
     Особенно
    0.85
    ぢ
    0.82
     diferentes
    0.81
     especialmente
    0.79
     báo
    0.79
    жуть
    0.79
     особенно
    0.78
     Currents
    0.77
    POSITIVE LOGITS
    d
    1.13
    n
    0.97
    t
    0.91
    re
    0.84
    g
    0.82
    m
    0.79
    ोदर
    0.79
    製
    0.79
    b
    0.76
    yr
    0.74
    Activations Density 0.000%

    No Known Activations