© 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. 100553
    Prev
    Next
    INDEX
    Explanations

    India government and elections

    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
     as
    -1.41
    \\
    -1.04
     smtplib
    -1.03
     those
    -0.98
     there
    -0.98
     mereka
    -0.96
    زيل
    -0.96
    </h4>
    -0.93
    来讲
    -0.91
    💫
    -0.91
    POSITIVE LOGITS
     India
    1.33
    izielle
    1.24
    tionen
    1.09
    ავ
    1.08
     ぶ
    1.04
     gradova
    1.03
    ğiniz
    1.02
    Сту
    1.02
    cuencia
    1.02
     inalámb
    1.02
    Activations Density 0.102%

    No Known Activations