© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61415
    Prev
    Next
    INDEX
    Explanations

    random, Q, EV, measuring

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

    The neuron activates on usages of random number generators or related identifiers (e.g. Random, rand, random).

    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
    出
    -1.75
    鲮
    -1.63
    Possibly
    -1.59
    ۥ
    -1.58
    ”,
    -1.58
    ”،
    -1.58
    .].
    -1.57
    artamento
    -1.52
    lysm
    -1.52
     ücret
    -1.47
    POSITIVE LOGITS
     biologie
    1.70
    脍
    1.68
     tomates
    1.64
     grec
    1.63
    formatie
    1.59
     penser
    1.58
     Rois
    1.55
     erreur
    1.55
     peluche
    1.55
     arabe
    1.53
    Activations Density 0.003%

    No Known Activations