© 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. 95416
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    lında
    -0.99
    maksi
    -0.98
     revelar
    -0.94
    posY
    -0.91
    ")==
    -0.90
     cruelty
    -0.89
    ]),
    -0.88
    menuhi
    -0.88
    äume
    -0.88
    óny
    -0.87
    POSITIVE LOGITS
     crests
    0.94
     exult
    0.94
    an
    0.91
    lor
    0.90
    vin
    0.90
     anise
    0.90
    les
    0.89
     OGSÅ
    0.87
     DATOS
    0.86
     gals
    0.84
    Activations Density 0.010%

    No Known Activations