© 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. 69220
    Prev
    Next
    INDEX
    Explanations

    bill vote

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

    debates about, math and, exact operating, stories quarter

    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
    فه
    0.52
     euc
    0.42
    氧
    0.42
    ող
    0.41
    词
    0.41
    Humidity
    0.41
    Wet
    0.41
     लेखन
    0.40
    湿
    0.40
    一个
    0.40
    POSITIVE LOGITS
     চেষ্টা
    0.51
    値段
    0.49
     иногда
    0.47
     япон
    0.46
    りたい
    0.46
     সাপ্তাহিক
    0.46
     तिथे
    0.46
     અમદાવાદ
    0.46
     dubai
    0.46
     Санкт
    0.45
    Activations Density 0.001%

    No Known Activations