© 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. 47478
    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
    の影響
    -1.37
    codiles
    -1.32
    凩
    -1.30
    gefügt
    -1.27
    齜
    -1.23
    ⎔
    -1.23
     Gestão
    -1.22
     gestern
    -1.20
    формация
    -1.20
     самый
    -1.20
    POSITIVE LOGITS
    Those
    1.52
    These
    1.35
    ândia
    1.24
     danse
    1.22
    …..
    1.21
     pouce
    1.20
    .....
    1.20
     dessas
    1.19
    They
    1.16
     Those
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.