© 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. 12086
    Prev
    Next
    INDEX
    Explanations

    programming generic types

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

    the opening angle bracket in generic type declarations (like `List<String>`, `Array<Int>`, `Dictionary<Position, Cell>`).

    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
     if
    -1.80
     at
    -1.78
     on
    -1.70
     you
    -1.67
    縊
    -1.62
     so
    -1.57
     but
    -1.52
     while
    -1.52
    there
    -1.48
     and
    -1.47
    POSITIVE LOGITS
    jenigen
    1.91
     auffi
    1.84
     baumwolle
    1.75
    訁
    1.71
    注意事
    1.70
    ：【
    1.60
    不管是
    1.59
     matériau
    1.55
    羮
    1.55
     ſever
    1.53
    Activations Density 0.008%

    No Known Activations