© 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. 10-GEMMASCOPE-RES-131K
    7. 7583
    Prev
    Next
    INDEX
    Explanations

    last names ending in common suffixes

    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
     the
    -2.36
     others
    -2.09
    叽
    -1.80
     their
    -1.76
     traditionellen
    -1.66
     varied
    -1.61
    ądz
    -1.59
     various
    -1.59
     other
    -1.59
     solchen
    -1.58
    POSITIVE LOGITS
    \
    1.69
    噲
    1.59
     mattino
    1.54
     problém
    1.43
     secoli
    1.42
     tedy
    1.39
     până
    1.35
    ेमाल
    1.34
     teda
    1.32
     yapan
    1.31
    Activations Density 0.116%

    No Known Activations