© 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. 34303
    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
     several
    -1.34
     many
    -1.28
     oddly
    -1.27
     helps
    -1.24
     gives
    -1.23
     an
    -1.22
     combines
    -1.22
     interestingly
    -1.21
     two
    -1.21
     quite
    -1.20
    POSITIVE LOGITS
     nivå
    1.42
    ܆
    1.34
     sentimentos
    1.34
     augmenter
    1.29
     écla
    1.28
     arrivant
    1.27
     plafon
    1.27
    Lorsque
    1.26
     сериала
    1.23
     kiu
    1.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.