© 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. 15736
    Prev
    Next
    INDEX
    Explanations

    actor inventory definitions

    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
     of
    -2.30
     which
    -1.47
     autre
    -1.42
     if
    -1.38
    了下去
    -1.33
     other
    -1.31
     or
    -1.30
    Ꮇ
    -1.26
    1
    -1.25
     FÜR
    -1.24
    POSITIVE LOGITS
    但她
    1.70
     a
    1.56
    akteur
    1.41
     how
    1.38
     perdeu
    1.37
     armazenamento
    1.34
    plantilla
    1.33
    adhyay
    1.31
    heast
    1.30
     bizarre
    1.30
    Activations Density 0.010%

    No Known Activations