© 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. 31838
    Prev
    Next
    INDEX
    Explanations

    Viruses and Miracles, Spanish and others

    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
    ב
    1.63
    т
    1.59
    ف
    1.38
    י
    1.35
    其他
    1.33
    ت
    1.27
    i
    1.27
    И
    1.26
    А
    1.20
    う
    1.20
    POSITIVE LOGITS
     pense
    1.35
    わけ
    1.34
    ag
    1.31
     Compaq
    1.31
    ेक्षित
    1.31
    ান্দ
    1.30
    ara
    1.26
     mondiale
    1.26
     ótima
    1.24
    തിരെ
    1.23
    Activations Density 0.002%

    No Known Activations