© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11799
    Prev
    Next
    INDEX
    Explanations

    formal greetings and addresses

    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
     not
    -1.82
     was
    -1.73
     It
    -1.45
    enuto
    -1.36
    懇
    -1.34
     things
    -1.32
     uživ
    -1.27
     todėl
    -1.27
    についての
    -1.26
    Chloride
    -1.25
    POSITIVE LOGITS
     kanton
    1.46
     WOOD
    1.45
    U
    1.44
    镲
    1.35
    踯
    1.34
     generell
    1.33
     aussit
    1.32
     hiver
    1.32
     zitate
    1.32
     investissements
    1.30
    Activations Density 0.023%

    No Known Activations