© 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. 11060
    Prev
    Next
    INDEX
    Explanations

    programming variable names

    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
     feier
    -1.13
     biały
    -1.06
    nyata
    -1.04
     nadru
    -1.02
     acoso
    -1.01
     sitesinde
    -1.01
    strukt
    -1.01
     Städten
    -1.00
    ğından
    -0.99
     takimi
    -0.99
    POSITIVE LOGITS
    を
    0.91
     egenskaper
    0.90
    iramente
    0.90
     Psychol
    0.90
    Common
    0.89
    ">
    0.89
    。　
    0.88
    ('$
    0.87
    asters
    0.86
    ynchrotron
    0.85
    Activations Density 0.002%

    No Known Activations