© 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. 7640
    Prev
    Next
    INDEX
    Explanations

    ixlib, ixid (image URLs)

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

    The neuron responds strongly to tokens in non-Latin scripts (e.g. Korean or other foreign‐language characters).

    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
     식으로
    0.62
    ונת
    0.61
    때
    0.61
    ffekt
    0.57
    getBlue
    0.55
    oprene
    0.54
    maketitle
    0.54
    aro
    0.54
     मोहब्बत
    0.54
    垲
    0.53
    POSITIVE LOGITS
    grid
    0.53
     curtain
    0.53
    循环
    0.53
    ροι
    0.53
     bookcase
    0.52
    circulation
    0.50
     Cerv
    0.50
    телно
    0.50
     попро
    0.50
     divisão
    0.48
    Activations Density 0.003%

    No Known Activations