© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72267
    Prev
    Next
    INDEX
    Explanations

    specific sequences after punctuation

    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
     ligeramente
    -1.98
    excellents
    -1.95
    痉
    -1.89
     például
    -1.89
    鉀
    -1.84
     réun
    -1.80
     moviliz
    -1.72
    erobic
    -1.71
     supuestamente
    -1.68
     Only
    -1.65
    POSITIVE LOGITS
     observa
    1.62
    nový
    1.61
     after
    1.61
     modifica
    1.60
     devia
    1.59
     organiza
    1.58
     medicina
    1.57
     specifica
    1.55
     ulter
    1.54
     autori
    1.50
    Activations Density 0.122%

    No Known Activations