© 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. 55250
    Prev
    Next
    INDEX
    Explanations

    ruled by, choices

    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
     coordinates
    0.53
    t
    0.49
    _
    0.46
     Courts
    0.46
     Governments
    0.46
    多
    0.46
     Positions
    0.45
     Councilor
    0.45
    ت
    0.45
    ل
    0.44
    POSITIVE LOGITS
     manusia
    0.54
    üren
    0.49
    ër
    0.47
    katore
    0.47
    dayspecial
    0.46
     baix
    0.46
     Мне
    0.45
    beni
    0.45
    dagen
    0.45
     étend
    0.45
    Activations Density 0.001%

    No Known Activations