© 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. 247037
    Prev
    Next
    INDEX
    Explanations

    viewing contexts, get, the third, Gypsy King, BOOLE AN, flexible, evening

    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
    Not in Any Lists

    No Comments

    Negative Logits
    cluso
    0.48
     Debido
    0.47
    梠
    0.47
     Página
    0.46
     تحت
    0.46
     ყველ
    0.46
    baixo
    0.46
     معظم
    0.44
     मारने
    0.44
     pequeñas
    0.44
    POSITIVE LOGITS
     midwifery
    0.52
     dní
    0.51
     gái
    0.48
    ജ്
    0.47
     並
    0.46
     magie
    0.46
    TRAVEL
    0.45
    st
    0.45
    aug
    0.44
    спомина
    0.44
    Activations Density 0.001%

    No Known Activations