© 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. 22-GEMMASCOPE-RES-131K
    7. 73828
    Prev
    Next
    INDEX
    Explanations

    jump conditions and overflow

    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
    sistence
    -1.09
    uyasha
    -1.04
    ·
    -1.03
    agues
    -1.01
    دل
    -1.00
    because
    -1.00
     sebenar
    -0.99
    juries
    -0.97
    💛
    -0.97
     their
    -0.96
    POSITIVE LOGITS
     Assim
    0.99
     occa
    0.95
     skolan
    0.93
     anfangs
    0.91
     desperdic
    0.88
     gifting
    0.88
    INNOV
    0.87
     nadie
    0.86
    當天
    0.84
    ัล
    0.84
    Activations Density 0.003%

    No Known Activations