© 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. 25121
    Prev
    Next
    INDEX
    Explanations

    code arguments and variables

    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
     if
    -1.40
     Entste
    -1.00
     while
    -1.00
     providing
    -0.98
     time
    -0.98
    ård
    -0.98
     as
    -0.97
     neither
    -0.96
     remove
    -0.94
    くださった
    -0.94
    POSITIVE LOGITS
     uninten
    1.08
    ération
    1.05
    depuis
    1.04
    水が
    1.03
    beginning
    1.03
    èle
    1.03
     estn
    1.02
    STARTING
    1.02
    voyez
    1.01
     zaraz
    1.01
    Activations Density 0.002%

    No Known Activations