© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64492
    Prev
    Next
    INDEX
    Explanations

    code constructs, data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ཿ
    -1.54
    鸲
    -1.40
    ⎔
    -1.38
     wacky
    -1.38
    戋
    -1.38
     quintessential
    -1.36
     cuatro
    -1.34
    槩
    -1.34
     verhind
    -1.34
    ਗ਼
    -1.33
    POSITIVE LOGITS
     although
    1.65
     after
    1.59
     while
    1.57
     every
    1.55
     even
    1.54
     with
    1.51
     by
    1.50
     as
    1.49
     because
    1.48
     during
    1.46
    Activations Density 0.001%

    No Known Activations