© 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. 71317
    Prev
    Next
    INDEX
    Explanations

    information and how-to queries

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

    scripting

    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
     பங்கே
    0.47
     전류
    0.46
     అధ్యక్షుడు
    0.46
    樣本
    0.45
     நன்கு
    0.45
     చక్క
    0.44
     раствора
    0.44
    䨋
    0.44
    జేపీ
    0.43
     музи
    0.43
    POSITIVE LOGITS
     from
    0.57
     with
    0.56
     due
    0.52
     $\
    0.52
     dereg
    0.52
     sua
    0.51
     notification
    0.51
     apabila
    0.51
     no
    0.51
     ser
    0.50
    Activations Density 0.002%

    No Known Activations