© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65392
    Prev
    Next
    INDEX
    Explanations

    Catalonia, Barcelona, Balearic Islands

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

    This neuron fires on Catalan-language tokens or proper names (e.g. “Català,” place and organization names in Catalan).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emporio
    -1.30
    خخ
    -1.27
    cartItems
    -1.24
    Desa
    -1.23
     lavadora
    -1.23
     bañera
    -1.23
    ஊ
    -1.23
    متن
    -1.19
    تحميل
    -1.18
    อย่างไร
    -1.18
    POSITIVE LOGITS
     kilometr
    1.25
    ï
    1.16
    xan
    1.14
    P
    1.14
     hà
    1.13
    A
    1.13
     coral
    1.12
    inh
    1.11
    EM
    1.10
     amarelo
    1.09
    Activations Density 0.018%

    No Known Activations