© 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. 107092
    Prev
    Next
    INDEX
    Explanations

    serial port configuration

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

    The neuron predominantly fires on numeric tokens and numeric literals (e.g. integers, version numbers, IDs).

    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
    vitational
    -0.79
    악
    -0.73
    γέν
    -0.71
    vspace
    -0.71
     lw
    -0.69
    WOW
    -0.68
    牛乳
    -0.68
    onded
    -0.68
     Bartholomew
    -0.68
    OMEM
    -0.67
    POSITIVE LOGITS
     serial
    0.88
     portu
    0.80
    pev
    0.80
    Shift
    0.77
    serializers
    0.77
     Shift
    0.76
     shift
    0.75
    serializer
    0.74
    therin
    0.74
    shift
    0.73
    Activations Density 0.047%

    No Known Activations