© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113390
    Prev
    Next
    INDEX
    Explanations

    The code types

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

    the opening angle bracket in generic type declarations (like `<T>` or `<String>`).

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

    This neuron detects the angle-bracket “<” token used to introduce generic type parameters in code.

    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
    顎
    -1.66
    -
    -1.66
     is
    -1.59
    侥
    -1.56
     '
    -1.56
     suministro
    -1.54
    我来
    -1.53
     entretenimiento
    -1.51
     earliest
    -1.48
    ører
    -1.47
    POSITIVE LOGITS
    O
    1.96
    if
    1.84
    0
    1.82
    r
    1.73
     видом
    1.65
    eclamp
    1.63
    D
    1.63
    e
    1.57
    n
    1.57
     {
    1.52
    Activations Density 0.002%

    No Known Activations