© 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. 1133
    Prev
    Next
    INDEX
    Explanations

    simple compound terms

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

    the neuron specifically detects occurrences of the identifier “Simple” (e.g. in class, module, or function names) within code snippets.

    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
    tlv
    -0.84
    有個
    -0.76
     Their
    -0.73
     Geden
    -0.71
     换
    -0.71
     to
    -0.69
    spare
    -0.69
     lát
    -0.66
     概念
    -0.66
     拿
    -0.65
    POSITIVE LOGITS
    xes
    1.04
    mente
    1.01
     prez
    0.93
    ">\
    0.91
    উ
    0.90
    getType
    0.90
    youtube
    0.90
    Skin
    0.88
    tude
    0.87
    enziale
    0.86
    Activations Density 0.023%

    No Known Activations