© 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. 4385
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on technical parameter or field names (often capitalized or camel-cased) in documentation.

    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
     unambiguous
    0.73
     instantaneous
    0.63
    0.63
     Rutherford
    0.63
     ungroup
    0.62
     outermost
    0.60
     maxillary
    0.59
     idempotent
    0.59
     $\
    0.59
     unital
    0.59
    POSITIVE LOGITS
    Restaurants
    0.65
    許多
    0.63
    譬
    0.63
    क्यों
    0.61
    raient
    0.61
    许多
    0.60
    Nau
    0.59
    Smiling
    0.59
    Many
    0.58
    कई
    0.58
    Activations Density 0.000%

    No Known Activations