© 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. 79688
    Prev
    Next
    INDEX
    Explanations

    Effect of, Assessment of

    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
     kazak
    -1.20
    RAINE
    -1.18
     Ilustra
    -1.04
     giy
    -1.03
     peugeot
    -1.02
    琊
    -0.99
     harap
    -0.98
     morales
    -0.98
     iny
    -0.98
     berkata
    -0.97
    POSITIVE LOGITS
    nerability
    1.09
    帖
    1.03
     bizony
    1.01
     otthon
    0.96
     кстати
    0.95
    の絵
    0.94
    šana
    0.94
     contended
    0.94
     F
    0.93
    اشتم
    0.93
    Activations Density 0.000%

    No Known Activations