© 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. 13264
    Prev
    Next
    INDEX
    Explanations

    its own unique attribute

    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
    ようになります
    -1.41
     agujero
    -1.33
    Isso
    -1.30
    啻
    -1.27
     artykuł
    -1.25
    hlar
    -1.23
     cuchillo
    -1.22
     equipaje
    -1.21
    ZIONE
    -1.20
     part
    -1.19
    POSITIVE LOGITS
     different
    1.66
     olika
    1.47
     with
    1.42
     this
    1.40
    不同的
    1.38
     when
    1.36
     lorsque
    1.30
    when
    1.27
    which
    1.27
     When
    1.27
    Activations Density 0.028%

    No Known Activations