© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148596
    Prev
    Next
    INDEX
    Explanations

    words following `may`, `Open`, `she`, `Developing`, `you`, `This`, `simple`, `curator`

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

    non-English languages

    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_31_width_262k_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
     năng
    0.47
     dragging
    0.46
    麸
    0.45
     handler
    0.44
    ἥ
    0.44
     নিয়ন্ত্রণ
    0.44
    foration
    0.44
     suất
    0.44
    ificazione
    0.44
     ट्रॉप
    0.43
    POSITIVE LOGITS
    พวก
    0.48
    కోండి
    0.48
    uje
    0.47
    ዶች
    0.46
    好事
    0.46
     পরিষদের
    0.45
    ¿
    0.45
     வீட்டில்
    0.45
     Coelho
    0.44
    வையில்
    0.44
    Activations Density 0.000%

    No Known Activations