© 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. 150067
    Prev
    Next
    INDEX
    Explanations

    family man

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

    foreign words and characters

    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
     паліты
    0.49
    sure
    0.49
     assessing
    0.49
    绮
    0.48
     Assessments
    0.47
     Imaging
    0.46
     individuals
    0.45
     discretion
    0.45
    rules
    0.45
     extrapol
    0.45
    POSITIVE LOGITS
    Wert
    0.51
    -"+
    0.50
    Greece
    0.49
    Bou
    0.45
    cvec
    0.45
    船
    0.45
    任務
    0.44
    玫瑰
    0.43
    Bola
    0.43
     プラス
    0.43
    Activations Density 0.000%

    No Known Activations