© 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. 34-GEMMASCOPE-RES-131K
    7. 47329
    Prev
    Next
    INDEX
    Explanations

    unit test or designation

    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_34/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
     personaggio
    -1.21
     большие
    -1.18
    さぎ
    -1.17
    tienda
    -1.12
    archiwizowane
    -1.11
     jepang
    -1.11
     arrivato
    -1.09
    欹
    -1.09
    sprzedam
    -1.04
     Lingkungan
    -1.03
    POSITIVE LOGITS
    Units
    1.52
     UNITS
    1.51
     Units
    1.45
     unit
    1.45
     Unit
    1.41
    Unit
    1.38
    unit
    1.34
    UNIT
    1.34
     units
    1.28
     UNIT
    1.28
    Activations Density 0.027%

    No Known Activations