© 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. 22-GEMMASCOPE-RES-131K
    7. 33470
    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
     zeven
    -1.48
     Verenigde
    -1.44
     سپس
    -1.41
    8
    -1.40
    1
    -1.39
     butik
    -1.38
    useNewUrlParser
    -1.36
     ideen
    -1.36
    3
    -1.35
    EMOS
    -1.34
    POSITIVE LOGITS
     ścian
    1.33
     frequenza
    1.24
    u
    1.23
     there
    1.22
     was
    1.20
    ↵
    1.16
    右側
    1.13
    あた
    1.13
    achelor
    1.12
     here
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.