© 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. 527
    Prev
    Next
    INDEX
    Explanations

    India judgment

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

    The neuron fires strongly on opening announcement or promotional headlines—that is, the introductory sentences that announce or introduce a new product, event, or offer.

    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
    0.54
    ,
    0.47
     s
    0.45
     in
    0.45
     de
    0.44
     d
    0.44
     is
    0.44
     e
    0.43
    .
    0.43
     and
    0.43
    POSITIVE LOGITS
    atthena
    0.46
    aloko
    0.42
    idiendo
    0.42
    utilizzo
    0.41
    éseket
    0.41
    avasena
    0.40
    endrá
    0.40
    humidité
    0.39
    śred
    0.39
    fromi
    0.39
    Activations Density 0.132%

    No Known Activations