© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38665
    Prev
    Next
    INDEX
    Explanations

    correctness and suitability

    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
     firs
    -1.45
    皛
    -1.44
    \|_{
    -1.44
     indecent
    -1.38
    ragende
    -1.37
    gians
    -1.36
    knowing
    -1.35
    大約
    -1.35
     listop
    -1.32
    vaccinated
    -1.32
    POSITIVE LOGITS
     what
    1.62
     also
    1.58
     really
    1.57
     a
    1.51
     does
    1.48
     fully
    1.45
     could
    1.42
     economic
    1.40
     good
    1.39
     well
    1.37
    Activations Density 0.031%

    No Known Activations