© 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. 75225
    Prev
    Next
    INDEX
    Explanations

    avoiding political and cultural issues

    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
    SetActive
    0.55
     無料
    0.51
     ቅ
    0.47
    ۊ
    0.46
     対象
    0.46
    助
    0.46
    ڼ
    0.46
     setActive
    0.46
     zicht
    0.45
     mieszkańców
    0.45
    POSITIVE LOGITS
    5
    0.68
    6
    0.64
    7
    0.51
    4
    0.50
    8
    0.48
    ५
    0.48
    aff
    0.45
    9
    0.44
    é
    0.43
    arak
    0.43
    Activations Density 0.002%

    No Known Activations