© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66833
    Prev
    Next
    INDEX
    Explanations

    code punctuation and directives

    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
     новом
    -1.04
     която
    -1.01
     successive
    -1.01
    營業時間
    -0.93
     peculiarities
    -0.91
     conseillers
    -0.91
     same
    -0.88
     consecutive
    -0.87
    试图
    -0.87
     befes
    -0.85
    POSITIVE LOGITS
     także
    1.03
    </b>
    1.02
     också
    0.96
    ︶
    0.96
    haled
    0.94
     además
    0.93
    vented
    0.90
     and
    0.89
    </i>
    0.89
     />
    0.89
    Activations Density 0.012%

    No Known Activations