© 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. 60111
    Prev
    Next
    INDEX
    Explanations

    cms and radiation

    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
    Even
    -0.89
    拍攝
    -0.88
     १
    -0.88
    jąca
    -0.87
    приєм
    -0.87
     préférences
    -0.85
     tişört
    -0.84
    Unlike
    -0.84
     sillä
    -0.82
    Which
    -0.82
    POSITIVE LOGITS
     and
    1.05
    cms
    0.99
     cms
    0.97
    PDOException
    0.96
    начально
    0.93
     erhi
    0.89
    Programma
    0.88
    øse
    0.88
     프로
    0.87
     민
    0.87
    Activations Density 0.002%

    No Known Activations