© 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. 65457
    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
     one
    -1.28
     considerable
    -1.13
     prominent
    -1.12
     version
    -1.12
     suitable
    -1.11
    snowy
    -1.11
    poppy
    -1.10
    kumpulan
    -1.10
    rainy
    -1.09
     pracuje
    -1.09
    POSITIVE LOGITS
    m
    1.03
    Уже
    1.02
     chanel
    1.00
     citroen
    0.99
     posteriori
    0.98
    either
    0.98
    d
    0.97
    b
    0.97
    Также
    0.97
     qualif
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.