© 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. 79953
    Prev
    Next
    INDEX
    Explanations

    lists of magazines

    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
    𖣘
    -2.36
     VERY
    -2.36
    
    -2.27
    躄
    -2.25
     ridiculously
    -2.19
    s
    -2.19
    埽
    -2.16
     unbelievably
    -2.13
     dismal
    -2.11
    在我
    -2.09
    POSITIVE LOGITS
     получила
    2.02
    襤
    1.96
     providing
    1.93
    </h3>
    1.91
     bois
    1.89
     markedly
    1.85
     uds
    1.83
     making
    1.80
    
    1.79
     achieving
    1.78
    Activations Density 0.011%

    No Known Activations