© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66926
    Prev
    Next
    INDEX
    Explanations

    names, places, and brands

    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
     діяльності
    -1.05
     trinken
    -1.02
     визна
    -1.01
     составляет
    -0.96
     okno
    -0.94
     aufmerksam
    -0.93
     called
    -0.93
     egyéb
    -0.93
     prostu
    -0.92
    melis
    -0.91
    POSITIVE LOGITS
     woh
    1.35
    thodoxy
    1.34
    ternut
    1.31
    termilk
    1.27
    othes
    1.26
    thodox
    1.24
    “,
    1.20
    oczes
    1.17
    ckeye
    1.17
    iamo
    1.16
    Activations Density 0.040%

    No Known Activations