© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2212
    Prev
    Next
    INDEX
    Explanations

    8-segment puzzle

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

    This neuron detects capitalized fragments of proper names—brand, company, and product names or 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
    Parrocchia
    0.50
     tropas
    0.50
     Fleurit
    0.49
     sdx
    0.49
     ক্যাথোডে
    0.49
    াইতে
    0.48
     poza
    0.47
    🛑
    0.47
    এবং
    0.47
     LikeLike
    0.47
    POSITIVE LOGITS
    喺
    0.64
    ́
    0.53
    ümüzde
    0.50
    咗
    0.50
    ⾃
    0.50
    VIDIA
    0.48
     数据
    0.47
     Vladimir
    0.46
     Архивная
    0.46
     policymakers
    0.46
    Activations Density 1.101%

    No Known Activations