© 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. 208040
    Prev
    Next
    INDEX
    Explanations

    codes and obligations

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

    offensive racial slur

    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
    0.42
     aussi
    0.40
     when
    0.40
     Chris
    0.39
     Auto
    0.38
     też
    0.37
    1
    0.37
     Music
    0.36
     Silicon
    0.36
     unexpected
    0.36
    POSITIVE LOGITS
     possibilit
    0.47
     목표
    0.46
     метою
    0.46
    셔야
    0.45
     должны
    0.44
    莗
    0.43
     обеспечить
    0.43
    峄
    0.42
     proposent
    0.42
     должна
    0.41
    Activations Density 0.003%

    No Known Activations