© 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. 34-GEMMASCOPE-RES-131K
    7. 30334
    Prev
    Next
    INDEX
    Explanations

    language specific markers

    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
    rana
    -0.85
    其中的
    -0.84
     via
    -0.81
     which
    -0.78
     plantas
    -0.77
    LayoutParams
    -0.77
    CONFIGURATION
    -0.74
     przekon
    -0.73
    ització
    -0.72
     Bunun
    -0.72
    POSITIVE LOGITS
     inflación
    1.00
    inspired
    0.84
    ormon
    0.83
     faciliter
    0.83
    Chand
    0.83
    र्शन
    0.81
     vantaggio
    0.81
    สร้าง
    0.81
     igualdad
    0.81
    ophila
    0.79
    Activations Density 0.004%

    No Known Activations