© 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. 226931
    Prev
    Next
    INDEX
    Explanations

    sports and specific descriptions

    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
    ни
    0.47
    جات
    0.47
    ーツ
    0.46
    ovenants
    0.45
    麽
    0.45
     Understanding
    0.45
    біт
    0.45
    าน
    0.44
     I
    0.43
     a
    0.42
    POSITIVE LOGITS
    Keb
    0.53
     দুর্দান্ত
    0.51
    ĝis
    0.50
    Entity
    0.49
    Enqueue
    0.49
     temor
    0.48
    constexpr
    0.48
    AssetsRequest
    0.48
    EndInit
    0.47
     ክብ
    0.47
    Activations Density 0.000%

    No Known Activations