© 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. 34-GEMMASCOPE-RES-131K
    7. 76678
    Prev
    Next
    INDEX
    Explanations

    title:

    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_34/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
    Kön
    -0.71
     memorandum
    -0.68
     ridurre
    -0.67
     DSG
    -0.65
    앱
    -0.65
    INSTANCE
    -0.64
     app
    -0.64
    اسخ
    -0.64
     分
    -0.64
    aufnahme
    -0.64
    POSITIVE LOGITS
    chada
    0.70
     lest
    0.70
    angk
    0.69
    quarelle
    0.68
     koul
    0.67
     orquí
    0.67
    nois
    0.65
    addWidget
    0.65
    grafías
    0.64
     koti
    0.64
    Activations Density 0.067%

    No Known Activations