© 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. 58327
    Prev
    Next
    INDEX
    Explanations

    Python class definitions

    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
    lässlich
    -0.88
    ☺☺
    -0.87
     menant
    -0.85
     بلکه
    -0.83
    chery
    -0.82
     bedien
    -0.82
    💁
    -0.82
     ليست
    -0.80
     samma
    -0.79
    💯
    -0.79
    POSITIVE LOGITS
     class
    1.21
     demasiado
    0.96
    class
    0.95
     @
    0.90
     differenza
    0.88
     sınıf
    0.85
     empleado
    0.83
    <bos>
    0.81
     geführt
    0.81
    dering
    0.81
    Activations Density 0.012%

    No Known Activations