© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 16963
    Prev
    Next
    INDEX
    Explanations

    X or another

    np_acts-logits-general · gemini-2.5-flash-lite

    language to another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     одино
    0.40
     ακόμα
    0.39
     Santi
    0.38
    )[:
    0.37
     أيضاً
    0.37
     satisfe
    0.36
    ृत्व
    0.36
    यरी
    0.36
    第三方
    0.35
    !!!");
    0.35
    POSITIVE LOGITS
     दूसरे
    0.74
     دوسرے
    0.69
     другому
    0.68
     दूसरों
    0.67
     दुसऱ्या
    0.62
     others
    0.60
     অন্যের
    0.59
    दूसरे
    0.58
     drugiej
    0.58
     অপরের
    0.57
    Activations Density 0.026%

    No Known Activations