© 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. 7937
    Prev
    Next
    INDEX
    Explanations

    programming code and headings

    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
     ‘
    -2.03
     bazı
    -1.98
     But
    -1.78
     :
    -1.78
     or
    -1.77
    月末
    -1.75
     was
    -1.72
     fırs
    -1.72
     $
    -1.70
     in
    -1.66
    POSITIVE LOGITS
    絰
    2.20
    鵙
    2.00
     Bacteriol
    1.95
    ি
    1.93
     augusti
    1.91
     mauva
    1.91
     Entomol
    1.84
     bele
    1.82
    </h1>
    1.80
    μ
    1.80
    Activations Density 0.001%

    No Known Activations