© 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. 84497
    Prev
    Next
    INDEX
    Explanations

    start of questions or definitions

    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_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
    edor
    -0.81
    MADRID
    -0.78
     administering
    -0.77
     Admin
    -0.72
    二次
    -0.71
    pore
    -0.68
     ADMIN
    -0.68
    ILog
    -0.67
    Algeria
    -0.66
     admin
    -0.66
    POSITIVE LOGITS
     Trails
    1.09
    Trails
    1.06
    アリ
    0.84
    permum
    0.84
    hase
    0.79
    trails
    0.78
     vainly
    0.78
     resonate
    0.77
     Zem
    0.77
     Estelle
    0.77
    Activations Density 0.009%

    No Known Activations