© 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. 28328
    Prev
    Next
    INDEX
    Explanations

    algebraic variable manipulation

    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
     utiliser
    -1.08
     unie
    -1.01
     bénéficiaire
    -0.96
     própri
    -0.94
     serwis
    -0.93
     echte
    -0.93
     utilização
    -0.91
     saludos
    -0.90
     المعيار
    -0.88
    AsyncResult
    -0.87
    POSITIVE LOGITS
     like
    1.02
     more
    1.01
    𝘢
    0.93
     Städ
    0.93
     expresar
    0.93
    𝘸
    0.90
     wieś
    0.90
    ężczy
    0.89
     wusste
    0.88
     where
    0.87
    Activations Density 0.029%

    No Known Activations