© 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. 103030
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    completed questionnaires, termination, minimization

    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
     protecting
    0.45
    self
    0.44
    [{}\
    0.43
    people
    0.42
     Latham
    0.42
    seud
    0.42
    茣
    0.42
    thing
    0.42
    sev
    0.42
     Jeong
    0.42
    POSITIVE LOGITS
     тэ
    0.49
    Ins
    0.49
    ोब
    0.47
    ו
    0.47
     час
    0.46
     парк
    0.46
     نوع
    0.46
     був
    0.45
     появился
    0.45
     н
    0.45
    Activations Density 0.000%

    No Known Activations