© 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. 10-GEMMASCOPE-RES-131K
    7. 21353
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
     eight
    -2.42
     five
    -2.31
     any
    -2.31
     seven
    -2.19
     nine
    -2.11
     one
    -2.06
     eleven
    -2.05
     three
    -2.03
     four
    -2.03
     six
    -2.02
    POSITIVE LOGITS
    跸
    1.84
    despite
    1.80
     !!!!
    1.78
     they
    1.74
     célèbre
    1.70
     exceedingly
    1.65
     insanely
    1.64
     ſtre
    1.64
     goofy
    1.64
     ſever
    1.63
    Activations Density 0.042%

    No Known Activations