© 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. 80603
    Prev
    Next
    INDEX
    Explanations

    Culminating words in culross, culpeper, culrain, culver

    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
     Altogether
    -2.83
     Through
    -2.67
     resuming
    -2.66
     Incidentally
    -2.66
    ).
    -2.58
     Surprisingly
    -2.53
     Ironically
    -2.52
    There
    -2.50
    </i>
    -2.48
     Undoubtedly
    -2.44
    POSITIVE LOGITS
    臯
    3.41
     cartões
    2.77
    茕
    2.75
    ᕮ
    2.66
     bezw
    2.53
    䛗
    2.44
    苼
    2.41
    
    2.39
    聼
    2.36
    </sup>
    2.34
    Activations Density 0.003%

    No Known Activations