© 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. 10-GEMMASCOPE-RES-131K
    7. 9123
    Prev
    Next
    INDEX
    Explanations

    sqlite database

    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
    </b>
    -3.55
    ↵
    -2.86
     –
    -2.53
    ࿚
    -2.39
    ates
    -2.39
     This
    -2.39
     But
    -2.38
    d
    -2.36
    T
    -2.33
    </h2>
    -2.31
    POSITIVE LOGITS
    
    2.94
    ﻒ
    2.77
    ዡ
    2.69
    replyreport
    2.53
     especializados
    2.48
     desnuda
    2.47
     provenientes
    2.39
     comprometido
    2.36
     valioso
    2.36
     rodeado
    2.30
    Activations Density 0.006%

    No Known Activations