© 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. 10-GEMMASCOPE-RES-131K
    7. 127489
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     verkau
    -1.23
     Gründen
    -1.16
    剮
    -1.16
    of
    -1.13
     alerted
    -1.11
     This
    -1.10
     demanded
    -1.10
     my
    -1.10
    Vri
    -1.10
    le
    -1.09
    POSITIVE LOGITS
     you
    1.63
     {
    1.63
     backen
    1.30
    荭
    1.29
     цветами
    1.27
    ℔
    1.27
     columnas
    1.25
    timme
    1.24
    नलोड
    1.23
     lavorato
    1.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.