© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40349
    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
     gwaran
    -1.13
     škoda
    -1.13
     lovingly
    -1.13
     nicio
    -1.10
     sweetly
    -1.08
     sorely
    -1.08
     someplace
    -1.07
    かん
    -1.04
    真実
    -1.04
     perfecting
    -1.03
    POSITIVE LOGITS
     “
    1.30
     „
    1.27
    Their
    1.18
    What
    1.16
    以及
    1.10
    ){\
    1.08
     &#
    1.08
    嘴唇
    1.08
    There
    1.06
    ängt
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.