© 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. 59615
    Prev
    Next
    INDEX
    Explanations

    or

    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
    queryInterface
    -1.39
    assertThrows
    -1.28
    ()}>
    -1.25
    silien
    -1.23
     possibly
    -1.23
    TypeCode
    -1.23
     Fig
    -1.20
     GmbH
    -1.17
    s
    -1.16
    _),
    -1.14
    POSITIVE LOGITS
     there
    1.78
     גם
    1.54
    Also
    1.51
     あと
    1.50
     rất
    1.45
    
    1.38
    envoyer
    1.35
    也會
    1.34
     Также
    1.33
     myös
    1.30
    Activations Density 0.066%

    No Known Activations