© 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. 22078
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     when
    -1.79
     this
    -1.68
     could
    -1.46
    鶯
    -1.44
    これを
    -1.40
     может
    -1.39
    佾
    -1.39
    when
    -1.39
    這個
    -1.39
     захворю
    -1.37
    POSITIVE LOGITS
     "
    1.41
    .
    1.34
    mostly
    1.27
    putting
    1.26
    Mostly
    1.24
    ꙰
    1.24
     rivales
    1.23
     представители
    1.19
     souligne
    1.18
    Truly
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.