© 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. 34-GEMMASCOPE-RES-131K
    7. 31226
    Prev
    Next
    INDEX
    Explanations

    byte related terms

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

    This neuron is triggered by the angle‐bracket and comma tokens used in generic type parameter lists (e.g. “<String, String>”).

    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
     data
    -2.08
    data
    -1.56
    数据
    -1.36
     Data
    -1.31
    Data
    -1.25
     данные
    -1.23
    データ
    -1.20
     DATA
    -1.10
     данных
    -1.09
    DATA
    -1.07
    POSITIVE LOGITS
     byte
    4.72
    byte
    4.56
    BYTE
    2.47
     bytes
    2.28
     Byte
    2.17
    Byte
    2.11
     BYTE
    2.09
    bytes
    1.97
     bite
    1.97
    字节
    1.74
    Activations Density 0.039%

    No Known Activations