© 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. 7169
    Prev
    Next
    INDEX
    Explanations

    synthetic, photosynthetic, sympathetic

    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
    e
    -4.25
    d
    -3.08
     mencion
    -2.98
    y
    -2.89
    翆
    -2.83
     operacional
    -2.67
    他也
    -2.66
    푆
    -2.53
    のだが
    -2.52
    also
    -2.50
    POSITIVE LOGITS
    ly
    5.38
    ～～
    2.80
     entscheid
    2.64
    庒
    2.34
     Former
    2.34
     الإسلامية
    2.27
    撄
    2.22
    </code>
    2.20
    ally
    2.17
    时候
    2.17
    Activations Density 0.019%

    No Known Activations