© 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. 10-GEMMASCOPE-RES-131K
    7. 83800
    Prev
    Next
    INDEX
    Explanations

    control panel, console, station, interface

    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
    Negative Logits
     to
    -2.27
     on
    -1.80
    1
    -1.51
    b
    -1.50
     any
    -1.48
     in
    -1.48
    h
    -1.44
    2
    -1.43
     but
    -1.42
     ANY
    -1.39
    POSITIVE LOGITS
     bateria
    1.67
     felpa
    1.65
     apartament
    1.60
     milliard
    1.59
     prodi
    1.57
     luni
    1.56
     dacia
    1.55
     interieur
    1.51
    tschaft
    1.49
     cabine
    1.49
    Activations Density 0.029%

    No Known Activations