© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119806
    Prev
    Next
    INDEX
    Explanations

    url anchors and headers

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

    the "#" symbol in URLs or file paths, particularly in HTML anchor links and documentation references.

    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
    );
    -1.73
    着头
    -1.59
    地看着
    -1.49
     vanligt
    -1.45
    Хо
    -1.42
    蓠
    -1.41
     típico
    -1.41
    Those
    -1.41
    If
    -1.39
     [];
    -1.34
    POSITIVE LOGITS
     of
    2.14
     that
    1.80
     each
    1.72
     a
    1.66
     this
    1.63
    guigu
    1.62
     recevrez
    1.59
     the
    1.55
     at
    1.55
    antası
    1.52
    Activations Density 0.000%

    No Known Activations