© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59611
    Prev
    Next
    INDEX
    Explanations

    programming class names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -1.77
     weiterhin
    -1.46
     künftig
    -1.37
     fornecer
    -1.30
     土豆
    -1.27
    confirmPassword
    -1.27
    complished
    -1.24
    MatInputModule
    -1.23
     diesmal
    -1.23
    }}{
    -1.22
    POSITIVE LOGITS
     also
    1.31
     cremallera
    1.27
     your
    1.27
    是一種
    1.25
    zamos
    1.24
     будь
    1.22
     such
    1.21
     there
    1.21
    ant
    1.20
     qualsiasi
    1.18
    Activations Density 0.287%

    No Known Activations