© 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. 22-GEMMASCOPE-RES-131K
    7. 26882
    Prev
    Next
    INDEX
    Explanations

    programming keywords and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     any
    -0.88
    ～」
    -0.83
    是啊
    -0.81
    فاف
    -0.81
    ühungen
    -0.80
     Luglio
    -0.79
    crowned
    -0.78
     cioccolato
    -0.77
    cnia
    -0.77
     geçti
    -0.77
    POSITIVE LOGITS
    ($(
    0.81
    了好
    0.78
    CONS
    0.76
     ズ
    0.76
    ilet
    0.76
    ће
    0.75
    了几
    0.73
     tecnologías
    0.73
     amd
    0.73
    DataObject
    0.72
    Activations Density 0.121%

    No Known Activations