© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104072
    Prev
    Next
    INDEX
    Explanations

    href attribute

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

    the `href` attribute in HTML and JavaScript code.

    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
    }
    -2.91
     be
    -2.61
     We
    -2.58
     It
    -2.33
     o
    -2.28
    !”
    -2.20
    );
    -2.19
    衿
    -2.14
    ubwa
    -2.13
    一刻
    -2.13
    POSITIVE LOGITS
    獁
    3.44
    2
    3.38
    to
    3.13
     alip
    2.59
     レスト
    2.55
    D
    2.53
     Paroles
    2.52
    襌
    2.50
     diza
    2.45
     malang
    2.44
    Activations Density 0.005%

    No Known Activations