© 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. 369
    Prev
    Next
    INDEX
    Explanations

    The neuron flags content‐bearing words—especially concrete nouns and key verbs—while ignoring function words.

    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
    .
    0.42
    が存在
    0.39
    。
    0.37
    ។
    0.37
    ۔
    0.36
    ։
    0.35
     。
    0.34
     존재
    0.33
     :
    0.33
     Existen
    0.33
    POSITIVE LOGITS
     during
    0.54
     عشان
    0.49
     щоб
    0.49
     أثناء
    0.48
     after
    0.48
     on
    0.47
     για
    0.47
    すぐに
    0.46
     لمدة
    0.46
     at
    0.46
    Activations Density 11.626%

    No Known Activations