© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103863
    Prev
    Next
    INDEX
    Explanations

    html document tags

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

    closing HTML document tags or references to HTML documents in code examples.

    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
     souvent
    -1.84
    ⃙
    -1.82
     stroj
    -1.79
    桄
    -1.77
    手帳
    -1.73
    襞
    -1.70
     Mereka
    -1.69
    ekw
    -1.67
    jeje
    -1.66
     rique
    -1.64
    POSITIVE LOGITS
    d
    2.72
    3
    2.69
    c
    2.56
    !
    2.56
    5
    2.33
    k
    2.27
    2
    2.25
    ma
    2.25
    4
    2.23
    lo
    2.20
    Activations Density 0.001%

    No Known Activations