© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 39188
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    it
    0.86
    ó
    0.85
    的气
    0.83
    olution
    0.77
    swith
    0.75
    iscilla
    0.75
    oy
    0.74
    o
    0.74
    withstanding
    0.73
    iles
    0.72
    POSITIVE LOGITS
     הה
    0.87
    कुछ
    0.81
     Noch
    0.81
     qualche
    0.80
     पहले
    0.75
     कुछ
    0.74
     вижу
    0.73
     spender
    0.72
     इ
    0.71
     أع
    0.71
    Activations Density 0.000%

    No Known Activations