© 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. 68912
    Prev
    Next
    INDEX
    Explanations

    else or catch block

    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
     malheur
    -1.15
    Thời
    -1.11
     ARXIV
    -1.02
     CLINICAL
    -1.00
    Tại
    -0.96
    setObject
    -0.95
    Ϟ
    -0.94
     Pearls
    -0.94
    鵙
    -0.93
    setAlpha
    -0.92
    POSITIVE LOGITS
    return
    1.69
     return
    1.13
    *
    1.05
     are
    1.00
     as
    0.94
    :
    0.93
     cannot
    0.93
     académica
    0.89
    r
    0.89
     constitutes
    0.87
    Activations Density 0.002%

    No Known Activations