© 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. 38640
    Prev
    Next
    INDEX
    Explanations

    introduce, found, and began

    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
    various
    -1.41
     -
    -1.39
     DIFFERENT
    -1.36
     —
    -1.34
     such
    -1.27
    different
    -1.25
     특
    -1.21
    не
    -1.20
     เช
    -1.18
     étudier
    -1.18
    POSITIVE LOGITS
     podía
    1.47
     or
    1.45
    🌹
    1.36
     deliciosa
    1.34
     hermos
    1.32
    Эти
    1.30
     because
    1.27
     these
    1.26
     setelah
    1.24
    decoração
    1.22
    Activations Density 0.138%

    No Known Activations