© 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. 12387
    Prev
    Next
    INDEX
    Explanations

    code class declarations

    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
    графия
    -1.52
     bleek
    -1.41
    ஶ
    -1.40
    闳
    -1.37
     but
    -1.36
    kinh
    -1.36
    我们可以
    -1.34
    郾
    -1.34
    </h6>
    -1.32
     polskiego
    -1.31
    POSITIVE LOGITS
    ’
    2.02
    7
    1.54
    y
    1.45
    となる
    1.42
    i
    1.41
     машины
    1.40
    :
    1.40
    |
    1.37
    _
    1.37
     rooster
    1.32
    Activations Density 0.009%

    No Known Activations