© 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. 129572
    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
     Schluß
    -1.41
     Très
    -1.27
     ستاره
    -1.27
    饹
    -1.24
    厛
    -1.21
    鲔
    -1.19
    ◖
    -1.16
     Toujours
    -1.16
     gött
    -1.16
     erklär
    -1.13
    POSITIVE LOGITS
     on
    1.31
    in
    1.25
    😤
    1.19
    !!"
    1.18
    ke
    1.16
    ☀️
    1.13
    HostException
    1.13
    je
    1.12
    á
    1.11
    ⫺
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.