© 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. 71171
    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
    niego
    -1.36
    8
    -1.31
    PLATES
    -1.30
     Independencia
    -1.23
     Nación
    -1.22
     methode
    -1.20
     katalog
    -1.19
    日起
    -1.18
     sayang
    -1.17
     Temporada
    -1.16
    POSITIVE LOGITS
    足够的
    1.47
    zellan
    1.27
     принял
    1.23
    较为
    1.23
    がありますが
    1.19
    があり
    1.17
    しますが
    1.16
     animosity
    1.16
    ginous
    1.10
    参考にして
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.