© 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-16K
    7. 15117
    Prev
    Next
    INDEX
    Explanations

    principle or Principal

    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_16k_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
    り
    2.41
    ação
    2.28
    ки
    2.23
    یوں
    2.05
    ول
    1.92
    が多く
    1.91
    Ки
    1.91
     usare
    1.88
    து
    1.84
     ambiente
    1.84
    POSITIVE LOGITS
    ている
    2.25
    ǚ
    1.86
    нің
    1.80
    didn
    1.78
    اً
    1.76
     violación
    1.73
    ர்
    1.70
     conlle
    1.70
     cít
    1.69
    τή
    1.61
    Activations Density 0.023%

    No Known Activations