© 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-65K
    7. 46319
    Prev
    Next
    INDEX
    Explanations

    depending on

    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_65k_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
     severely
    0.64
     prejudiced
    0.57
    ！
    0.55
     semua
    0.54
    ،
    0.54
     unanimous
    0.54
     inherently
    0.52
    ，
    0.52
     retracted
    0.51
    １
    0.51
    POSITIVE LOGITS
    ת
    0.57
    Depending
    0.56
    Adress
    0.52
    CUIT
    0.50
    The
    0.48
    อาจ
    0.48
    та
    0.48
    ACIÓN
    0.47
    ли
    0.46
    PA
    0.46
    Activations Density 0.034%

    No Known Activations