© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28591
    Prev
    Next
    INDEX
    Explanations

    noun phrases

    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
     mauva
    -1.71
    奩
    -1.63
     acheter
    -1.60
     triko
    -1.60
     isolamento
    -1.53
    
    -1.52
     alho
    -1.51
     médicaux
    -1.50
    鹩
    -1.49
     .......
    -1.48
    POSITIVE LOGITS
    </h2>
    2.34
     with
    2.00
     by
    1.92
     on
    1.91
    </i>
    1.86
     from
    1.84
    </b>
    1.83
     in
    1.80
    </em>
    1.79
     and
    1.77
    Activations Density 0.019%

    No Known Activations