© 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. 60106
    Prev
    Next
    INDEX
    Explanations

    domain names

    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
     our
    -2.39
     their
    -1.96
     the
    -1.83
     vermelha
    -1.73
     those
    -1.70
    蘆
    -1.70
     Gespräche
    -1.68
    我家
    -1.63
     überras
    -1.60
     欣赏
    -1.58
    POSITIVE LOGITS
    ’
    1.95
    ↵↵
    1.57
    ogues
    1.44
     fase
    1.42
    gens
    1.41
    ！！！
    1.41
    :')
    1.38
    </h1>
    1.34
     '=
    1.34
     eau
    1.33
    Activations Density 0.064%

    No Known Activations