© 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. 40147
    Prev
    Next
    INDEX
    Explanations

    Greek letters and math symbols

    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
    at
    -2.91
    as
    -2.55
     новых
    -2.11
     ‘
    -2.02
     nuevas
    -1.98
    你就
    -1.91
    很好的
    -1.85
    蕻
    -1.81
     новой
    -1.80
     entwick
    -1.77
    POSITIVE LOGITS
     It
    2.36
    ities
    2.19
    ꪔ
    1.93
    ⃙
    1.86
     signifikan
    1.84
    砗
    1.83
     mirador
    1.80
    </td>
    1.80
     obligación
    1.77
    攫
    1.77
    Activations Density 0.010%

    No Known Activations