© 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. 22-GEMMASCOPE-RES-131K
    7. 72950
    Prev
    Next
    INDEX
    Explanations

    Jamaica dub reggae

    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_22/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>
    -2.22
    </sub>
    -1.68
     humanas
    -1.61
    身后的
    -1.59
    ="")
    -1.57
     yapılır
    -1.57
     nemici
    -1.55
    無い
    -1.53
     grafico
    -1.52
    越是
    -1.52
    POSITIVE LOGITS
    (
    1.57
     maler
    1.52
    )
    1.48
    простра
    1.47
    ↵
    1.42
    :
    1.41
     konsep
    1.39
     требует
    1.35
    攫
    1.33
    </b>
    1.32
    Activations Density 0.012%

    No Known Activations