© 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. 101831
    Prev
    Next
    INDEX
    Explanations

    image URLs and file paths

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

    HTML image source attributes, specifically the `src="` portion in `<img>` tags and URL paths.

    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
    h
    -1.38
    mathrm
    -1.34
    est
    -1.30
    [
    -1.28
     jsou
    -1.28
    $
    -1.27
    ”，
    -1.27
    d
    -1.27
    s
    -1.25
    她的
    -1.21
    POSITIVE LOGITS
     from
    2.09
    خفض
    1.52
    Wady
    1.46
     first
    1.43
     zusätz
    1.38
    erintah
    1.38
    Mvh
    1.37
     nossas
    1.37
    푢
    1.35
     übri
    1.34
    Activations Density 0.010%

    No Known Activations