© 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. 240148
    Prev
    Next
    INDEX
    Explanations

    words from various languages

    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
    b
    0.54
    r
    0.46
    R
    0.46
    T
    0.46
    l
    0.45
    OT
    0.45
    H
    0.45
    졸
    0.45
    зю
    0.44
    J
    0.44
    POSITIVE LOGITS
     कार्यक्रम
    0.55
     velik
    0.54
     तेलंगाना
    0.53
     diversidad
    0.51
     আল্লাহর
    0.51
     cifra
    0.50
     minha
    0.48
     conocida
    0.48
     mexicanos
    0.48
     realidad
    0.48
    Activations Density 0.001%

    No Known Activations