© 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. 184157
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

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

    effects, conditions, or requirements

    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
     चू
    0.46
    점으로
    0.46
     Shree
    0.46
     Shub
    0.45
     შ
    0.45
    ದ್ದು
    0.44
     മാസ
    0.43
     uncompromising
    0.42
     उंची
    0.42
     ჭ
    0.42
    POSITIVE LOGITS
    лой
    0.54
    本土
    0.50
    сков
    0.49
    hilfe
    0.49
    legt
    0.47
    alte
    0.46
     bekl
    0.46
    רט
    0.45
    et
    0.44
    ليل
    0.43
    Activations Density 0.002%

    No Known Activations