© 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. 34-GEMMASCOPE-RES-131K
    7. 106522
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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_34/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
     not
    -1.45
     both
    -1.36
     only
    -1.35
    There
    -1.35
     even
    -1.35
     with
    -1.32
     for
    -1.32
     there
    -1.30
    Using
    -1.29
     eneste
    -1.29
    POSITIVE LOGITS
     wacky
    1.21
     convain
    1.20
     goofy
    1.20
    が付いて
    1.16
     diversos
    1.14
     feront
    1.13
     dismal
    1.11
     sooo
    1.10
     wondrous
    1.09
     individuelle
    1.08
    Activations Density 0.007%

    No Known Activations