© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41452
    Prev
    Next
    INDEX
    Explanations

    foreign concepts and multilingual terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.55
    on
    0.54
    letter
    0.49
    piece
    0.49
    know
    0.49
    font
    0.48
    text
    0.48
    '
    0.48
    most
    0.47
    em
    0.47
    POSITIVE LOGITS
     Ayam
    0.56
     ટીમ
    0.53
    耂
    0.51
     Гуляць
    0.50
    墒
    0.50
     mises
    0.50
     Букмекерлер
    0.50
    ᶤ
    0.50
    雰
    0.49
    竪
    0.49
    Activations Density 0.000%

    No Known Activations