© 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. 10-GEMMASCOPE-RES-131K
    7. 119927
    Prev
    Next
    INDEX
    Explanations

    buoy and buoyancy

    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_10/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
     benessere
    -2.56
     paziente
    -2.56
     ottima
    -2.48
     ursprünglichen
    -2.45
     Ensuring
    -2.41
     pulsante
    -2.38
     Betrach
    -2.36
     Untersuch
    -2.36
     parere
    -2.34
     Veränder
    -2.31
    POSITIVE LOGITS
    '
    3.48
    {
    2.75
    \
    2.34
    ]
    2.31
    *
    2.31
    瓛
    2.23
    "
    2.14
    ),
    2.05
    ྜ
    1.99
    %
    1.97
    Activations Density 0.002%

    No Known Activations