© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9445
    Prev
    Next
    INDEX
    Explanations

    biological and scientific names

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

    The neuron activates strongly on capitalized proper names—people’s names, place names, and other named entities.

    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_31_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
     Aix
    0.41
     _
    0.38
     Arbeits
    0.38
     Barth
    0.37
     Zeitschr
    0.37
     Deaf
    0.35
     Olga
    0.35
     Army
    0.35
     subjekt
    0.35
     Atelier
    0.35
    POSITIVE LOGITS
    osilicate
    0.54
    ol
    0.50
    u
    0.46
    al
    0.46
    ak
    0.45
    on
    0.45
    icione
    0.45
    il
    0.45
    acées
    0.45
    ip
    0.45
    Activations Density 0.331%

    No Known Activations