© 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. 170720
    Prev
    Next
    INDEX
    Explanations

    whale spout

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

    stack up ingredients

    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
     for
    0.52
    for
    0.51
     của
    0.49
     of
    0.48
     throughout
    0.45
     from
    0.44
     without
    0.43
    裡
    0.43
     Nebraska
    0.43
     исторических
    0.43
    POSITIVE LOGITS
     някои
    0.47
     některé
    0.45
     alarmed
    0.44
    Ahora
    0.44
     সমস্যাবলী
    0.44
     bazı
    0.43
    अब
    0.43
    Појединачна
    0.43
    援助
    0.42
     unele
    0.42
    Activations Density 0.000%

    No Known Activations