© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26297
    Prev
    Next
    INDEX
    Explanations

    questions and their answers

    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
     would
    -1.48
    ♪♪
    -1.37
     will
    -1.30
     wouldn
    -1.29
     couldn
    -1.28
    ₁(
    -1.23
    @@@@
    -1.19
     whoſe
    -1.16
    cocina
    -1.16
     asiática
    -1.15
    POSITIVE LOGITS
     been
    1.63
     not
    1.51
     also
    1.46
     be
    1.43
    not
    1.40
     ever
    1.38
     etc
    1.34
     run
    1.30
     now
    1.27
     taken
    1.24
    Activations Density 0.065%

    No Known Activations