© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28497
    Prev
    Next
    INDEX
    Explanations

    SQL query parameters

    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
     of
    -1.28
    芣
    -1.23
     mengganggu
    -1.05
     misto
    -1.05
     nagu
    -1.03
     nya
    -1.02
     vernis
    -0.96
     prata
    -0.95
     persil
    -0.95
     became
    -0.95
    POSITIVE LOGITS
     extremadamente
    1.16
     hinten
    1.09
    ље
    1.02
     asomb
    1.02
     angebra
    0.99
    rict
    0.98
     adherent
    0.96
     introducir
    0.95
    inary
    0.95
     intertw
    0.94
    Activations Density 0.000%

    No Known Activations