© 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. 101738
    Prev
    Next
    INDEX
    Explanations

    exception ; server ; handler

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

    class names in Java import statements, particularly compound names with capital letters (camel case identifiers).

    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
     a
    -2.33
     are
    -1.98
     to
    -1.97
     if
    -1.87
     respective
    -1.70
     {
    -1.65
     -
    -1.61
    !
    -1.61
     said
    -1.59
     '
    -1.59
    POSITIVE LOGITS
    <bos>
    2.16
    雠
    1.73
     பய
    1.71
    Ⓚ
    1.60
     récomp
    1.55
     dingen
    1.50
    那些
    1.48
    erráneo
    1.47
     réponses
    1.45
     beweging
    1.45
    Activations Density 0.096%

    No Known Activations