© 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. 6891
    Prev
    Next
    INDEX
    Explanations

    The neuron flags the key topic words or names—especially prominent nouns and proper nouns—that headline or summarize each text segment.

    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
    Salon
    0.71
     প্রস্তুতি
    0.70
    Vt
    0.68
     फ्ला
    0.66
    Este
    0.64
    Nuestro
    0.64
     Neighborhood
    0.63
    垒
    0.63
    林
    0.63
    Cook
    0.62
    POSITIVE LOGITS
     иногда
    1.07
     sendo
    1.00
     обычно
    0.99
     frequentemente
    0.94
     geralmente
    0.93
     пес
    0.92
     ás
    0.89
     tendo
    0.88
     полное
    0.88
     funções
    0.85
    Activations Density 0.000%

    No Known Activations