© 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. 1306
    Prev
    Next
    INDEX
    Explanations

    artículo indefinido la

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

    The neuron fires on non-English (especially Italian/Spanish) words, i.e. foreign‐language tokens.

    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
     with
    0.48
     also
    0.47
    并且
    0.46
    d
    0.46
    with
    0.44
    0
    0.44
    F
    0.44
    by
    0.44
    also
    0.43
    s
    0.43
    POSITIVE LOGITS
     poucos
    0.61
     parceria
    0.60
     utilização
    0.58
     vários
    0.55
     várias
    0.55
     inú
    0.55
     solução
    0.54
     relação
    0.54
     aplicação
    0.54
     apresentação
    0.54
    Activations Density 0.044%

    No Known Activations