© 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. 16268
    Prev
    Next
    INDEX
    Explanations

    axis, index, xticks, xlim, bar

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

    The neuron selectively fires on unusually rare or long content words—i.e. it flags low‐frequency, multi‐syllable vocabulary items.

    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
    锺
    0.90
    lists
    0.88
     iż
    0.88
     ausgewählt
    0.85
    coprote
    0.83
    uv
    0.80
    selectable
    0.80
    blocks
    0.79
    Grav
    0.78
    Epid
    0.78
    POSITIVE LOGITS
    ப்பெ
    0.83
     national
    0.75
     shed
    0.73
    ド
    0.73
     crore
    0.72
     pays
    0.71
     indul
    0.71
     comb
    0.70
     sull
    0.70
     psy
    0.69
    Activations Density 0.000%

    No Known Activations