© 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. 3891
    Prev
    Next
    INDEX
    Explanations

    all that apply

    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
    3.08
    कर
    2.70
    いた
    2.41
    ação
    2.36
    ج
    2.34
    서
    2.34
    daki
    2.33
    ول
    2.27
    து
    2.23
    сть
    2.23
    POSITIVE LOGITS
    িখিত
    2.05
     iż
    1.90
    ্পনিক
    1.88
    儘
    1.88
    ྥ
    1.88
    اً
    1.85
     związ
    1.76
     privind
    1.74
     carico
    1.74
    uwen
    1.71
    Activations Density 0.124%

    No Known Activations