© 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. 22-GEMMASCOPE-RES-131K
    4. 70670
    Prev
    Next
    INDEX
    Explanations

    qualitative and quantitative analysis

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

    The neuron activates on scholarly research–style method and analysis terminology (e.g. “chi-square analysis,” “qualitative,” “quantitative,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    calculator
    -0.85
    argento
    -0.83
    哭了
    -0.81
     авгу
    -0.81
    計算
    -0.80
     Cyril
    -0.77
     xxvi
    -0.75
    ре
    -0.74
     NACIONAL
    -0.73
    tt
    -0.73
    POSITIVE LOGITS
     कीजिए
    0.84
    setScene
    0.82
    Üdv
    0.82
     Basta
    0.82
    ppchen
    0.81
    issements
    0.81
    屍
    0.81
    endencia
    0.80
    yesi
    0.80
     Arrest
    0.80
    Activations Density 0.120%

    No Known Activations