© 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. 10-GEMMASCOPE-RES-131K
    7. 66903
    Prev
    Next
    INDEX
    Explanations

    perturbation and fluctuation

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

    This neuron detects technical terms related to scientific perturbations and oscillations.

    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
    f
    -1.70
    4
    -1.69
    ２
    -1.54
    ７
    -1.52
     pratique
    -1.48
    p
    -1.47
     會
    -1.45
    最初
    -1.41
    ５
    -1.41
    最初の
    -1.41
    POSITIVE LOGITS
    が見える
    1.47
    %%%%
    1.45
     the
    1.45
    './
    1.40
    ÍAS
    1.39
    に関して
    1.38
    と呼ばれる
    1.38
    sibilità
    1.37
    はもちろん
    1.34
     ($('#
    1.32
    Activations Density 0.026%

    No Known Activations