© 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. 4302
    Prev
    Next
    INDEX
    Explanations

    contextual conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly fires on structural breaks (blank lines or section‐heading separators) in the document.

    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
     unequiv
    0.59
     hypersur
    0.58
    '!
    0.58
    !',
    0.56
     verifies
    0.55
    afstand
    0.55
     rêves
    0.55
    귿
    0.54
     сезо
    0.54
     '),
    0.54
    POSITIVE LOGITS
     Hence
    0.66
     Enquanto
    0.61
     Saat
    0.60
     Pues
    0.59
     While
    0.58
     Sehingga
    0.58
     But
    0.58
     GALLERY
    0.58
     Gallery
    0.57
     Providing
    0.57
    Activations Density 0.002%

    No Known Activations