© 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. 32774
    Prev
    Next
    INDEX
    Explanations

    calculus derivative questions

    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
     זיי
    -1.11
    豋
    -1.10
     oogen
    -1.09
     bied
    -1.07
    ㈯
    -1.05
     autonomie
    -1.03
     Marín
    -1.02
    ißt
    -1.00
     familien
    -1.00
     balans
    -1.00
    POSITIVE LOGITS
     of
    1.30
     at
    1.26
     his
    1.12
     now
    1.11
     Meksiku
    1.10
     You
    1.05
    娃娃
    1.05
     seus
    1.05
     we
    1.02
     as
    1.00
    Activations Density 0.028%

    No Known Activations