© 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. 34976
    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
     you
    -1.35
     last
    -1.24
     and
    -1.19
     
    -1.17
     for
    -1.09
     Nước
    -1.09
    <em>
    -1.08
    <strong>
    -1.05
     from
    -1.05
    沒有
    -1.05
    POSITIVE LOGITS
     giras
    1.39
     giacca
    1.38
    囿
    1.33
    rizona
    1.30
    Informazioni
    1.27
     conciertos
    1.26
     fuit
    1.25
     citas
    1.23
     victorias
    1.23
    riceps
    1.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.