© 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. 10528
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on relatively uncommon or specialized content words—particularly rare vocabulary and named entities.

    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
    0.91
     cerebrospinal
    0.84
     Hickory
    0.78
    ところに
    0.75
     зро
    0.75
    ے
    0.75
     Bypass
    0.74
    ırl
    0.74
     FOLLOW
    0.74
     Scotts
    0.73
    POSITIVE LOGITS
    fate
    0.93
    factor
    0.91
    en
    0.89
    fif
    0.86
    al
    0.84
    faktor
    0.84
    at
    0.82
    ap
    0.81
    Waste
    0.80
    t
    0.80
    Activations Density 0.000%

    No Known Activations