© 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. 229745
    Prev
    Next
    INDEX
    Explanations

    actions and outcomes

    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
    洳
    0.47
    Лі
    0.45
    lı
    0.44
    Ли
    0.44
    则是
    0.44
    لی
    0.44
    anio
    0.44
    خری
    0.43
    AppConstant
    0.43
    蠱
    0.43
    POSITIVE LOGITS
     dapur
    0.47
     kitchen
    0.44
     CARE
    0.43
     behandling
    0.43
     preparar
    0.41
     erstmal
    0.41
     erfolgen
    0.41
     pros
    0.40
     JAN
    0.40
     troopers
    0.40
    Activations Density 0.001%

    No Known Activations