© 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. 2764
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    This is where

    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
    ::
    0.54
    inak
    0.47
    *)
    0.47
    f
    0.46
    c
    0.45
     how
    0.45
    enthal
    0.45
    how
    0.44
    yuan
    0.44
    )
    0.43
    POSITIVE LOGITS
     কীটপত
    0.54
    🆈
    0.52
     পাকিস্তানিদের
    0.50
    ीडियो
    0.49
     indican
    0.49
    ्रोल
    0.48
     বাহিরে
    0.48
     ಪುಸ್ತಕ
    0.48
    疇
    0.48
     cependant
    0.48
    Activations Density 0.000%

    No Known Activations