© 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. 106517
    Prev
    Next
    INDEX
    Explanations

    learning related to structured content

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

    Entities Beyond Mr

    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
     doodles
    0.55
    ):
    0.52
     serie
    0.48
     pago
    0.48
     u
    0.47
     sum
    0.47
     sezon
    0.47
     paranormal
    0.46
    tt
    0.46
     serial
    0.46
    POSITIVE LOGITS
    ᱧ
    0.51
    全部
    0.47
    بع
    0.46
    ᙱ
    0.46
    太多
    0.45
    太过
    0.45
    рец
    0.44
    лера
    0.44
    ਡੇ
    0.44
    мір
    0.44
    Activations Density 0.000%

    No Known Activations