© 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. 34119
    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
     enlightening
    -1.41
     unquestionably
    -1.29
     unequivocally
    -1.28
     expressly
    -1.27
     escalating
    -1.27
     appalling
    -1.27
     hindering
    -1.26
     contentious
    -1.24
     zapato
    -1.23
     crippling
    -1.22
    POSITIVE LOGITS
    。
    1.31
    —-
    1.27
    ————
    1.14
     verlie
    1.05
    .-(
    1.05
    她
    1.04
    ."—
    1.03
    ——-
    1.03
     ongeveer
    1.02
    where
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.