© 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. 7612
    Prev
    Next
    INDEX
    Explanations

    draft picks and rounds

    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
     testé
    -1.49
    IC
    -1.48
    NOT
    -1.47
     "../../../../
    -1.45
    not
    -1.45
    その
    -1.40
    to
    -1.36
     Triathlon
    -1.34
     and
    -1.33
     Valorant
    -1.33
    POSITIVE LOGITS
     in
    1.55
    apatilla
    1.48
     what
    1.43
     people
    1.36
     ilman
    1.30
     todėl
    1.30
     an
    1.27
     your
    1.25
     more
    1.24
    hbs
    1.23
    Activations Density 0.019%

    No Known Activations