© 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. 170723
    Prev
    Next
    INDEX
    Explanations

    foreign language identifiers

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

    class D

    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
    VAT
    0.50
     pensions
    0.49
    そして
    0.48
    مد
    0.47
    맞
    0.47
     touristic
    0.46
     pensioner
    0.45
    まずは
    0.45
    賜
    0.44
    畯
    0.44
    POSITIVE LOGITS
    ni
    0.49
     企业
    0.49
     Xia
    0.45
     Shouldn
    0.44
     एक्टिव
    0.44
     Wouldn
    0.43
     Activated
    0.43
    were
    0.42
     എത്ത
    0.41
     scarcity
    0.41
    Activations Density 0.002%

    No Known Activations