© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103247
    Prev
    Next
    INDEX
    Explanations

    Delphi programming language

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

    the word "Delphi" (a programming language and IDE, or geographical/historical references to the ancient Greek site).

    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
    2
    -2.75
    3
    -2.44
    1
    -2.44
    the
    -2.38
    Approximately
    -2.38
    t
    -2.36
    {
    -2.34
    非常的
    -2.34
     neuf
    -2.31
    Possibly
    -2.30
    POSITIVE LOGITS
    béco
    2.28
    DECEMBER
    2.20
    nání
    2.19
    钊
    2.17
    er
    2.17
    伱
    2.14
    莘
    2.13
    籐
    2.11
    zação
    2.09
    ୌ
    2.09
    Activations Density 0.018%

    No Known Activations