© 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. 128035
    Prev
    Next
    INDEX
    Explanations

    explaining how things work

    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
    Not in Any Lists

    No Comments

    Negative Logits
     although
    -1.11
     only
    -1.11
     despite
    -1.07
    ждать
    -1.07
     not
    -1.04
     this
    -1.04
     just
    -0.98
    Ẓ
    -0.97
     our
    -0.95
     arba
    -0.95
    POSITIVE LOGITS
     их
    1.38
     also
    1.23
     broader
    1.19
    把它
    1.15
     também
    1.15
     también
    1.14
    それを
    1.13
     jejich
    1.13
    (**
    1.12
     также
    1.07
    Activations Density 0.076%

    No Known Activations