© 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. 199010
    Prev
    Next
    INDEX
    Explanations

    arrogance

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

    differentiate unique explanations

    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
     ridiculed
    0.46
    攽
    0.45
     बाळा
    0.45
    رداری
    0.44
     ridicule
    0.43
     کۆ
    0.42
     متحدہ
    0.42
     टकराव
    0.42
    |,
    0.42
    的人生
    0.42
    POSITIVE LOGITS
    stopped
    0.51
    룸
    0.50
    sexual
    0.50
    head
    0.46
    bury
    0.46
    ния
    0.46
    ined
    0.45
    nest
    0.45
    adjustable
    0.45
    reas
    0.44
    Activations Density 0.001%

    No Known Activations