© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205174
    Prev
    Next
    INDEX
    Explanations

    multilingual text and common phrases

    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
    ן
    0.54
    墺
    0.53
     Sử
    0.45
    TRA
    0.43
    ায়ত্ত
    0.42
    स्ट्र
    0.41
     TRAILS
    0.41
     PR
    0.41
     RADIO
    0.41
    ação
    0.41
    POSITIVE LOGITS
     terug
    0.47
    кинуло
    0.46
    liang
    0.46
    ج
    0.46
    ل
    0.45
    were
    0.45
     schl
    0.44
     вопросы
    0.44
    ngl
    0.44
     studente
    0.44
    Activations Density 0.000%

    No Known Activations