© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113250
    Prev
    Next
    INDEX
    Explanations

    html/xml closing tags

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

    forward slashes used as separators or delimiters in text.

    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
     erste
    -1.74
     omdat
    -1.59
     einigen
    -1.55
    it
    -1.54
     gracioso
    -1.49
     perpé
    -1.45
    an
    -1.43
    \
    -1.38
     utilizado
    -1.36
     vodu
    -1.36
    POSITIVE LOGITS
    jning
    1.59
    vénients
    1.52
     ചെയ
    1.47
    鈇
    1.47
     espon
    1.34
    czyna
    1.34
     veng
    1.31
    Happ
    1.31
     aix
    1.30
    ał
    1.29
    Activations Density 0.004%

    No Known Activations