© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113771
    Prev
    Next
    INDEX
    Explanations

    design and aesthetics

    np_acts-logits-general · gemini-2.5-flash-lite

    ethical, aesthetic, safety, mediation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Karena
    0.45
     Karena
    0.43
    ﻤ
    0.42
     dahil
    0.41
    ila
    0.41
    因為
    0.41
    лдуу
    0.40
    /(
    0.40
    /
    0.40
    !!”
    0.39
    POSITIVE LOGITS
     aesthetics
    0.65
     aesthetic
    0.58
     ultraviolet
    0.57
     Aesthetics
    0.56
     Ultraviolet
    0.55
     streetwear
    0.54
     experimentation
    0.52
    审美
    0.52
     iconography
    0.52
     रंगों
    0.51
    Activations Density 0.001%

    No Known Activations