© 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. 34-GEMMASCOPE-RES-131K
    7. 55900
    Prev
    Next
    INDEX
    Explanations

    referring to speakers or addressees

    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_34/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
    =”
    -1.05
     polski
    -1.04
     -"
    -1.00
     employé
    -1.00
    :”
    -1.00
     ônibus
    -0.98
    —"
    -0.98
     („
    -0.98
     ™
    -0.97
    咳咳
    -0.97
    POSITIVE LOGITS
     I
    2.02
     We
    1.64
     we
    1.59
    We
    1.52
     You
    1.50
    You
    1.47
     you
    1.43
     我
    1.39
     Oh
    1.38
    Your
    1.34
    Activations Density 0.058%

    No Known Activations