© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15248
    Prev
    Next
    INDEX
    Explanations

    dishwasher, Q:, China, Iso-

    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
    玏
    -1.77
     撮っ
    -1.74
    鵟
    -1.69
    琑
    -1.67
    kadot
    -1.66
     Saltar
    -1.63
    鏵
    -1.59
     Vereinigten
    -1.59
    礴
    -1.55
     <=",
    -1.55
    POSITIVE LOGITS
    '
    2.06
    </h3>
    2.05
    </i>
    1.73
     your
    1.64
    lt
    1.63
    ные
    1.55
    <bos>
    1.52
     tell
    1.50
     destacados
    1.48
                
    1.43
    Activations Density 0.007%

    No Known Activations