© 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. 34-GEMMASCOPE-RES-131K
    7. 59928
    Prev
    Next
    INDEX
    Explanations

    hotels, beaches, motels, cities, landscapes

    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_34/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
     炒め
    -1.29
    rawn
    -1.14
    ※※
    -1.13
    翆
    -1.13
    +),
    -1.10
    *?
    -1.07
    =“
    -1.05
    namental
    -1.05
     練習
    -1.04
     PHILOS
    -1.03
    POSITIVE LOGITS
     -
    1.20
    Again
    1.16
     presentará
    1.08
    着丈
    1.05
     or
    1.05
     Again
    1.04
     volverá
    1.02
     is
    1.01
     abandonné
    1.00
    Your
    0.98
    Activations Density 0.062%

    No Known Activations