© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101273
    Prev
    Next
    INDEX
    Explanations

    URL paths with numbers and slashes

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

    forward slashes in URLs, particularly in the path portion after the domain name.

    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
    着一个
    -1.46
    ERS
    -1.34
    すみません
    -1.29
    瑧
    -1.23
    IndexPath
    -1.23
     Там
    -1.20
    armes
    -1.20
    uppo
    -1.18
    zlo
    -1.16
    他会
    -1.16
    POSITIVE LOGITS
     –
    1.58
    jährige
    1.44
     then
    1.40
    σεων
    1.40
     =
    1.27
     -
    1.27
    甚至
    1.25
    класс
    1.24
    лся
    1.23
     можно
    1.23
    Activations Density 0.052%

    No Known Activations