© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 339
    Prev
    Next
    INDEX
    Explanations

    multilingual tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    cj
    1.01
     Эти
    0.86
    
    0.86
    dj
    0.85
     Raman
    0.84
     LABORATOR
    0.84
    ssia
    0.82
    CLUSIVE
    0.82
    cm
    0.82
    sss
    0.81
    POSITIVE LOGITS
    вропей
    0.80
     derniers
    0.79
    з
    0.77
     übers
    0.73
    تب
    0.73
    oscill
    0.72
    ارب
    0.71
     effectivement
    0.71
     proč
    0.71
    них
    0.70
    Activations Density 0.000%

    No Known Activations