© 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. 16-GEMMASCOPE-2-RES-262K
    7. 34981
    Prev
    Next
    INDEX
    Explanations

    unwrap operations

    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_16_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
    ानी
    0.70
    Você
    0.69
    Quando
    0.65
    ios
    0.64
    Indonesia
    0.64
    ک
    0.62
    Ре
    0.61
    Сан
    0.61
    Y
    0.61
    ier
    0.61
    POSITIVE LOGITS
     كلمات
    0.57
     gering
    0.54
    ানু
    0.52
    辩
    0.51
    ższ
    0.48
     T
    0.48
     μεγάλη
    0.47
     comment
    0.47
     spricht
    0.46
     hoch
    0.46
    Activations Density 0.001%

    No Known Activations