© 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. 133642
    Prev
    Next
    INDEX
    Explanations

    foreign words and units

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

    list of comma separated values

    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
     將
    0.51
     ư
    0.49
    ोन
    0.46
    向
    0.46
    会将
    0.46
    Buildings
    0.45
     rt
    0.44
     खोलने
    0.44
     Antwerp
    0.44
     并
    0.44
    POSITIVE LOGITS
     кило
    0.55
    疲れ
    0.47
     сле
    0.47
     гори
    0.46
    الس
    0.46
     kilo
    0.44
    착
    0.43
     arenas
    0.43
     hunters
    0.42
    лям
    0.42
    Activations Density 0.000%

    No Known Activations