© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27328
    Prev
    Next
    INDEX
    Explanations

    colors or hex codes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     v
    -1.31
     how
    -1.26
     and
    -1.25
     even
    -1.23
     if
    -1.20
     of
    -1.20
     E
    -1.16
    !
    -1.16
    V
    -1.16
     V
    -1.15
    POSITIVE LOGITS
    Hå
    1.45
    Sü
    1.38
    Zdrav
    1.38
    Gön
    1.34
    Mü
    1.34
    Grafik
    1.32
    Rü
    1.32
    Matthias
    1.32
    Laut
    1.30
    Laos
    1.30
    Activations Density 0.004%

    No Known Activations