© 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. 41334
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases and prepositions

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

    city names and locations

    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
    क्शंस
    0.47
    넛
    0.46
     मेरा
    0.46
    歡
    0.46
    гийн
    0.45
    rond
    0.44
     ग्लोबल
    0.44
    цкі
    0.44
    카드
    0.44
    남
    0.44
    POSITIVE LOGITS
    Tester
    0.41
     sogar
    0.39
     addirittura
    0.39
     কেবল
    0.39
     কিরূপে
    0.39
    াকাল
    0.39
    VERBOSE
    0.38
     中的
    0.38
     στον
    0.38
     gentle
    0.38
    Activations Density 0.000%

    No Known Activations