© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8944
    Prev
    Next
    INDEX
    Explanations

    c# code and spanish words

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

    The neuron lights up on content‐bearing open‐class words (nouns and adjectives) rather than on function words.

    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
    t
    0.75
    u
    0.75
     اب
    0.74
    ੁ
    0.73
     Abu
    0.73
     cartel
    0.72
    _
    0.70
    𝒆
    0.70
     Hiro
    0.70
    葷
    0.70
    POSITIVE LOGITS
     dielectric
    0.91
     frente
    0.75
    лья
    0.75
     기본
    0.75
     diferentes
    0.75
     останавли
    0.75
     ecmaVersion
    0.75
    女朋友
    0.74
    drawable
    0.73
    长期
    0.72
    Activations Density 0.001%

    No Known Activations