© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 193
    Prev
    Next
    INDEX
    Explanations

    scientists and who

    np_acts-logits-general · gemini-2.5-flash-lite

    people in roles and relative clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autofocus
    0.27
    0.27
     used
    0.27
    を使う
    0.26
     ใช้
    0.26
    text
    0.26
     გამოყენ
    0.25
     x
    0.25
     usamos
    0.25
     was
    0.25
    POSITIVE LOGITS
     who
    0.52
     ktorí
    0.52
     quienes
    0.51
     الذين
    0.47
     quien
    0.46
     whom
    0.44
     którzy
    0.44
     kteří
    0.39
     जिन्होंने
    0.38
    whom
    0.37
    Activations Density 2.397%

    No Known Activations