© 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. 68590
    Prev
    Next
    INDEX
    Explanations

    exceptions and invalid data

    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
     carrefour
    -1.15
     serp
    -1.08
     castell
    -1.05
     territo
    -1.05
     departement
    -1.02
     valentin
    -1.02
     prenn
    -1.00
    ✨✨
    -0.99
     katun
    -0.99
    Бер
    -0.97
    POSITIVE LOGITS
     same
    1.10
     ricas
    1.05
     cortas
    1.05
    (!__
    0.99
     not
    0.99
    ,
    0.95
     or
    0.95
     adatto
    0.94
    ruptedException
    0.93
     dim
    0.93
    Activations Density 0.014%

    No Known Activations