© 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. 33777
    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
    思议
    -1.12
    ogues
    -1.05
     meri
    -0.96
    שְׁ
    -0.93
    stuffs
    -0.93
     虫
    -0.91
     NOO
    -0.90
    遑
    -0.89
     amal
    -0.88
    )　
    -0.88
    POSITIVE LOGITS
    <0xA3>
    1.05
     that
    1.04
     zprávy
    0.99
    ropractor
    0.96
     here
    0.94
     najdete
    0.93
    [])
    0.92
    abstractmethod
    0.92
    richlet
    0.92
     тук
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.