© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86291
    Prev
    Next
    INDEX
    Explanations

    buzzing and humming sounds

    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
    〠
    -2.23
     местных
    -2.20
     маленьких
    -2.17
    悧
    -2.13
    泐
    -2.11
     astonishing
    -2.09
     diez
    -2.06
    ごめんなさい
    -2.06
    </h5>
    -2.05
    </h3>
    -2.03
    POSITIVE LOGITS
    '
    2.33
     奶
    2.06
    $
    2.03
    硨
    2.03
     That
    2.00
    \\
    1.98
    但他
    1.97
    лил
    1.94
    лили
    1.86
    但是在
    1.84
    Activations Density 0.003%

    No Known Activations