© 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. 64483
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
     promesse
    -1.18
     parfois
    -1.17
    Either
    -1.16
     séances
    -1.10
    often
    -1.09
     autre
    -1.09
    боров
    -1.09
    appellant
    -1.07
    somewhat
    -1.06
    ⅖
    -1.05
    POSITIVE LOGITS
     would
    1.23
     two
    1.18
     several
    1.17
     flera
    1.11
     three
    1.05
     only
    1.02
     various
    1.01
     mehreren
    0.98
     nahezu
    0.97
    ukseen
    0.97
    Activations Density 0.040%

    No Known Activations