© 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. 10-GEMMASCOPE-RES-131K
    7. 10447
    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
     when
    -2.97
     gets
    -2.75
     gives
    -2.67
     makes
    -2.58
    {
    -2.44
     at
    -2.42
     During
    -2.42
     delivers
    -2.39
     Usually
    -2.39
     takes
    -2.38
    POSITIVE LOGITS
    ⭓
    2.45
     Dinas
    2.22
    ౫
    2.14
    ౮
    2.13
     delightfully
    2.05
     astonishing
    2.02
     stunning
    2.00
     produkter
    1.99
    ౩
    1.98
     deliciously
    1.98
    Activations Density 0.000%

    No Known Activations