© 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. 12296
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on emphatic qualifiers—strong adjectives or adverbs (e.g. “unusual,” “unique,” “quite,” “incredibly,” “such”) used to intensify or emphasize a description.

    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
    y
    0.92
    й
    0.90
    ي
    0.88
    sons
    0.79
    odil
    0.78
    ня
    0.77
    ığı
    0.77
    沩
    0.75
    skin
    0.73
    sgem
    0.73
    POSITIVE LOGITS
     कराई
    0.69
     יותר
    0.65
     Archivlink
    0.64
    Hercules
    0.64
    /-/
    0.64
     Eurasia
    0.63
    </h2>
    0.62
     Př
    0.60
     antisymmetric
    0.59
     reschedule
    0.58
    Activations Density 0.000%

    No Known Activations