© 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. 27723
    Prev
    Next
    INDEX
    Explanations

    abstract

    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
     แต่
    -2.86
    莇
    -2.75
    鵙
    -2.64
     utilisés
    -2.59
    蓠
    -2.50
     ſever
    -2.48
     creat
    -2.48
     The
    -2.42
     soooo
    -2.38
     conteúdos
    -2.33
    POSITIVE LOGITS
     unrelenting
    3.30
     ostensibly
    3.06
     Surprisingly
    2.94
     burgeoning
    2.94
     exquisitely
    2.92
     undeniably
    2.88
    酲
    2.84
     diminish
    2.81
     Putting
    2.78
     longstanding
    2.77
    Activations Density 0.017%

    No Known Activations