© 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. 34-GEMMASCOPE-RES-131K
    7. 1235
    Prev
    Next
    INDEX
    Explanations

    C# data types and generics

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

    The neuron strongly fires on the angle‐bracket tokens (“<” and “>”) used in generic type declarations and parameter lists, i.e. it detects generic‐type syntax.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Thar
    -0.82
    jamento
    -0.79
    今日の
    -0.79
     franchi
    -0.78
    gså
    -0.77
    ő
    -0.77
     لهذا
    -0.77
     débat
    -0.75
     rhum
    -0.74
    থা
    -0.74
    POSITIVE LOGITS
     string
    1.34
    string
    1.33
     object
    1.27
    object
    1.27
     bool
    1.24
     long
    1.13
     int
    1.12
    ulong
    1.06
     global
    1.04
     short
    1.02
    Activations Density 0.008%

    No Known Activations