© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11986
    Prev
    Next
    INDEX
    Explanations

    people or role 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
     was
    -2.42
     etc
    -1.94
     does
    -1.84
     where
    -1.83
     is
    -1.75
    ↵↵
    -1.75
    It
    -1.73
     When
    -1.73
     ,
    -1.71
    R
    -1.71
    POSITIVE LOGITS
     to
    1.93
    凄く
    1.73
     espoir
    1.73
     menyen
    1.69
     karte
    1.65
     будущем
    1.63
    dann
    1.63
    垟
    1.63
    sich
    1.61
     aussit
    1.61
    Activations Density 0.082%

    No Known Activations