© 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. 8373
    Prev
    Next
    INDEX
    Explanations

    Country Armour systems

    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
    さぁ
    -2.06
     dijeron
    -2.05
     haine
    -1.93
     gefährlich
    -1.91
    ụp
    -1.91
     کامل
    -1.86
     facilitar
    -1.83
    攻击
    -1.82
    壜
    -1.81
     rafra
    -1.80
    POSITIVE LOGITS
    </em>
    2.56
     für
    2.44
     \
    2.33
    亖
    2.27
     для
    2.19
     эту
    2.19
     et
    2.09
    This
    2.02
    此事
    2.00
     común
    1.98
    Activations Density 0.023%

    No Known Activations