© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33810
    Prev
    Next
    INDEX
    Explanations

    code and file paths

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

    The neuron responds to tokens containing digits (e.g. numeric literals, version numbers, and placeholder identifiers like std::placeholders::_1).

    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
    儉
    -0.83
     خدمة
    -0.77
    RTEX
    -0.75
    Operate
    -0.73
    حت
    -0.72
    slika
    -0.71
     ní
    -0.71
     HCV
    -0.71
     campeonato
    -0.70
     باسم
    -0.70
    POSITIVE LOGITS
    testing
    0.91
    ptures
    0.78
     Perl
    0.78
     adhesives
    0.78
     perl
    0.78
     Platte
    0.77
     testing
    0.76
    скольку
    0.73
     postId
    0.73
     reconhecimento
    0.72
    Activations Density 0.020%

    No Known Activations