© 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. 7245
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and code snippets

    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
    \
    -3.14
    s
    -2.91
    </b>
    -2.89
    昔から
    -2.75
    たくさんの
    -2.41
    朝から
    -2.41
    但这
    -2.34
     to
    -2.31
    ほとんど
    -2.28
    たまに
    -2.25
    POSITIVE LOGITS
     vorigen
    3.38
    تیجه
    2.92
    </h3>
    2.89
    </em>
    2.84
    沨
    2.78
    褙
    2.67
    禵
    2.52
     dritten
    2.48
    旆
    2.47
     civilización
    2.42
    Activations Density 0.000%

    No Known Activations