© 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. 226768
    Prev
    Next
    INDEX
    Explanations

    section/descriptionCarbon derivedadvisers move

    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
     Toll
    0.48
     Ferien
    0.46
     Rowling
    0.46
     Fakt
    0.46
     Lula
    0.46
     Lösung
    0.45
     Temperatur
    0.45
     宋
    0.45
     উচ্চার
    0.44
     KAHN
    0.44
    POSITIVE LOGITS
    im
    0.53
    communities
    0.52
    uf
    0.50
    ou
    0.50
    et
    0.48
    ut
    0.48
    optim
    0.48
    ad
    0.47
    esses
    0.47
    jz
    0.47
    Activations Density 0.003%

    No Known Activations