© 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. 6856
    Prev
    Next
    INDEX
    Explanations

    Transactions

    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
    ﺻ
    0.86
    issner
    0.81
    n
    0.79
    ponden
    0.78
     dogged
    0.78
    ﺼ
    0.77
    vány
    0.77
    َات
    0.76
    ponse
    0.76
    шений
    0.75
    POSITIVE LOGITS
    ก
    0.98
    ב
    0.93
    तर
    0.92
    ε
    0.92
    קו
    0.89
    Codigo
    0.89
    ป
    0.88
    ระหว่าง
    0.87
    ربي
    0.87
    บ
    0.85
    Activations Density 0.001%

    No Known Activations