© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68374
    Prev
    Next
    INDEX
    Explanations

    real estate

    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_10/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
     of
    -1.61
     AND
    -1.50
     glaring
    -1.47
     harika
    -1.46
     TO
    -1.42
     illuminating
    -1.42
     eminently
    -1.38
     diarios
    -1.38
     [
    -1.38
     And
    -1.36
    POSITIVE LOGITS
     Descargar
    1.70
     daniel
    1.70
    aliśmy
    1.70
    issä
    1.68
     carlo
    1.66
     MARIA
    1.62
     zune
    1.62
     sige
    1.60
    équipement
    1.57
    ..”
    1.57
    Activations Density 0.006%

    No Known Activations