© 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. 212065
    Prev
    Next
    INDEX
    Explanations

    cargo, dog, African

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

    Transformer models further aggression

    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
    Negative Logits
    𝐳
    0.42
    lycer
    0.42
    女子
    0.41
    𝐛
    0.41
     mengatur
    0.40
    电气
    0.39
     meisjes
    0.38
     At
    0.38
    ٹری
    0.38
    awi
    0.37
    POSITIVE LOGITS
    =
    0.49
    會
    0.42
    肯
    0.41
     hoặc
    0.40
     кеңсе
    0.40
    、
    0.39
     vs
    0.39
    IDTH
    0.38
    atedral
    0.37
     recette
    0.37
    Activations Density 0.001%

    No Known Activations