© 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. 10-GEMMASCOPE-RES-131K
    7. 100792
    Prev
    Next
    INDEX
    Explanations

    destabilization and balance

    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
    </h3>
    -2.25
     можно
    -2.09
     soste
    -1.74
    h
    -1.74
     häufigsten
    -1.67
     melaporkan
    -1.66
    When
    -1.66
     essayé
    -1.65
     Gradually
    -1.62
    o
    -1.59
    POSITIVE LOGITS
    $,
    1.74
    鯢
    1.69
    尨
    1.68
    鹛
    1.55
     Noël
    1.52
    狆
    1.52
    ⢓
    1.51
     UNITY
    1.51
    鈇
    1.51
     you
    1.50
    Activations Density 0.021%

    No Known Activations