© 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. 25021
    Prev
    Next
    INDEX
    Explanations

    role of

    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
    .‏
    -1.52
    eamiento
    -1.41
    )):
    -1.38
     LIABLE
    -1.35
    řízen
    -1.35
    ensitive
    -1.33
     antigüedad
    -1.32
     pueblos
    -1.30
    因为它
    -1.30
    pleft
    -1.29
    POSITIVE LOGITS
     of
    4.00
     to
    1.57
    ためには
    1.30
     پنجم
    1.26
    ing
    1.26
     \
    1.21
     ufficiali
    1.21
     dette
    1.20
    を開始
    1.18
     tämä
    1.17
    Activations Density 0.205%

    No Known Activations