© 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. 22547
    Prev
    Next
    INDEX
    Explanations

    code parsing

    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
    م
    0.80
    ون
    0.72
    ز
    0.68
    ী
    0.65
    ة
    0.62
    CO
    0.61
    CH
    0.60
    ود
    0.59
    、
    0.59
    ف
    0.58
    POSITIVE LOGITS
     използ
    0.64
     на
    0.61
     от
    0.60
     были
    0.59
     цик
    0.58
    렜
    0.57
     за
    0.57
    ственных
    0.56
    řed
    0.56
     вершин
    0.55
    Activations Density 0.006%

    No Known Activations