© 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. 10-GEMMASCOPE-RES-131K
    7. 102967
    Prev
    Next
    INDEX
    Explanations

    would-be or aspiring nouns

    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
     Usa
    -2.02
    粜
    -1.95
     ventes
    -1.80
     opérateur
    -1.77
    有著
    -1.75
    later
    -1.74
     fortal
    -1.73
    among
    -1.73
    えっ
    -1.71
    あぁ
    -1.70
    POSITIVE LOGITS
     However
    1.96
     Since
    1.86
     as
    1.79
     at
    1.79
     That
    1.77
     of
    1.76
     encompassing
    1.73
     Interestingly
    1.68
     also
    1.66
     Would
    1.66
    Activations Density 0.007%

    No Known Activations