© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11289
    Prev
    Next
    INDEX
    Explanations

    social research and norms

    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_40_width_16k_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
     dwt
    0.45
     interfer
    0.45
     inherently
    0.44
     piani
    0.44
     narrativa
    0.43
    窠
    0.42
     protagon
    0.41
     potência
    0.41
    畐
    0.41
     tố
    0.41
    POSITIVE LOGITS
     sociological
    1.03
     sociology
    0.99
     Sociology
    0.99
     sociologist
    0.95
     Soci
    0.87
    SOCIAL
    0.85
    social
    0.84
     사회
    0.83
     Social
    0.82
     social
    0.81
    Activations Density 0.103%

    No Known Activations