© 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. 113639
    Prev
    Next
    INDEX
    Explanations

    template syntax and code references

    np_acts-logits-general · gemini-2.5-flash-lite

    HTML and code syntax elements, particularly opening tags, template delimiters, and structural markup.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    了出来
    -1.39
     typelib
    -1.37
     idée
    -1.30
     also
    -1.30
     sabias
    -1.28
    驒
    -1.27
    Schule
    -1.27
     $[
    -1.23
    ไม่มี
    -1.23
    翆
    -1.23
    POSITIVE LOGITS
    .”
    1.76
    y
    1.34
     meadow
    1.30
     zufrieden
    1.29
    us
    1.29
    at
    1.29
    ?
    1.28
     lousy
    1.27
    ？”
    1.24
     estadounidenses
    1.23
    Activations Density 0.070%

    No Known Activations