© 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. 104087
    Prev
    Next
    INDEX
    Explanations

    interface or type definitions

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

    the letter "I" when it appears as an interface prefix in programming code (like "IStartupFilter", "IApplicationBuilder", "IConstraint").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on the standalone uppercase “I” token, as used to start C# interface or generic‐type names (e.g. IApplicationBuilder, IValueConverter).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    al
    -3.25
    to
    -3.00
    h
    -2.67
    l
    -2.59
    n
    -2.59
    p
    -2.58
    ll
    -2.45
    c
    -2.42
    lt
    -2.39
    ur
    -2.34
    POSITIVE LOGITS
    TryDecode
    2.33
    źdz
    2.20
    品的
    2.17
    oggi
    2.16
     sabias
    2.14
    瑧
    2.02
     protestas
    1.96
    ubahan
    1.95
    ladı
    1.94
    Inggris
    1.92
    Activations Density 0.016%

    No Known Activations