© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13363
    Prev
    Next
    INDEX
    Explanations

    places with descriptive clauses

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

    The neuron preferentially activates on content‐bearing nouns (i.e. common nouns denoting people, places, or things).

    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
    /
    0.71
    (
    0.60
    для
    0.59
     optionally
    0.59
     another
    0.58
     eğer
    0.57
     dill
    0.55
    ForThe
    0.55
     evaluations
    0.55
     omissions
    0.55
    POSITIVE LOGITS
     spanning
    0.55
     الذي
    0.52
    whose
    0.52
    ที่มี
    0.52
     cuyos
    0.51
    ቷ
    0.51
     שנ
    0.49
     whose
    0.49
     ponctué
    0.49
    ที่
    0.48
    Activations Density 0.005%

    No Known Activations