© 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. 85363
    Prev
    Next
    INDEX
    Explanations

    even or odd spacing

    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
     by
    -2.08
     if
    -2.06
     It
    -1.82
     to
    -1.72
     because
    -1.66
     unquestionably
    -1.65
     as
    -1.64
     in
    -1.64
     when
    -1.62
     there
    -1.61
    POSITIVE LOGITS
    ars
    1.52
     fecond
    1.48
    and
    1.45
     elef
    1.42
     touristique
    1.41
    :</
    1.38
     urat
    1.37
    Egy
    1.34
    шают
    1.34
    𞤢
    1.32
    Activations Density 0.001%

    No Known Activations