© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34754
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     emphasizing
    -1.27
     emanating
    -1.24
     devastated
    -1.24
     heightened
    -1.22
     showcasing
    -1.20
     unequivocally
    -1.19
    裡的
    -1.18
    ꠥ
    -1.16
     instantaneously
    -1.16
    tahui
    -1.16
    POSITIVE LOGITS
     JOH
    1.27
    金
    1.23
     Japon
    1.21
     fyr
    1.17
    japan
    1.17
    論
    1.16
    8
    1.16
     👎
    1.15
     tomat
    1.15
     ſol
    1.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.