© 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. 119388
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

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

    closing curly braces in code blocks.

    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
    しました
    -1.37
     of
    -1.34
    としている
    -1.29
     excru
    -1.29
     tattered
    -1.26
    してます
    -1.24
    ,
    -1.23
    Está
    -1.22
    枷
    -1.21
    Estás
    -1.20
    POSITIVE LOGITS
     \
    1.65
    ’
    1.45
    $*$
    1.41
     arba
    1.35
     on
    1.34
    \*
    1.34
    猀
    1.34
    ӧ
    1.27
    iation
    1.27
    sss
    1.27
    Activations Density 0.007%

    No Known Activations