© 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. 11176
    Prev
    Next
    INDEX
    Explanations

    suit or series history

    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
    直至
    -1.23
     -->
    -1.11
     питання
    -1.06
     dois
    -1.05
     membag
    -1.02
     noved
    -1.02
    _%
    -1.01
     bumbu
    -1.01
     viernes
    -1.01
     cuer
    -1.01
    POSITIVE LOGITS
     пожалуйста
    1.13
     variétés
    1.10
    ressive
    1.08
    รี
    1.03
     языка
    1.00
    upassen
    0.99
     ребенку
    0.97
     ক
    0.96
    omalies
    0.95
    iseite
    0.94
    Activations Density 0.028%

    No Known Activations