© 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. 13919
    Prev
    Next
    INDEX
    Explanations

    html class names

    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
    );
    -1.50
     diciendo
    -1.45
     the
    -1.45
    が多い
    -1.37
    ཋ
    -1.35
    槩
    -1.34
    Of
    -1.34
     is
    -1.33
    );
    -1.32
    apic
    -1.30
    POSITIVE LOGITS
    呖
    1.58
     體
    1.53
     samh
    1.50
     彈
    1.48
    tifiable
    1.44
    ittaa
    1.43
     業
    1.42
    neous
    1.41
    デメリット
    1.40
    aneity
    1.40
    Activations Density 0.000%

    No Known Activations