© 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. 128115
    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
     after
    -1.30
     September
    -1.27
     as
    -1.27
     many
    -1.22
     while
    -1.16
     in
    -1.11
     After
    -1.09
     meticulously
    -1.09
     Although
    -1.09
     October
    -1.07
    POSITIVE LOGITS
     Internazionale
    1.14
    ecie
    1.11
    DESCRIP
    1.07
     quadrado
    1.05
     découver
    1.04
     Huffington
    1.02
     xadrez
    1.01
     vocale
    1.01
     الثاني
    1.00
     velho
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.