© 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. 15364
    Prev
    Next
    INDEX
    Explanations

    freedom and choice

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

    freedom and autonomy

    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
    ורה
    0.39
     menyer
    0.39
     недоста
    0.38
    ettes
    0.38
     היו
    0.37
     المت
    0.36
     Etiquetas
    0.36
    慚
    0.36
    ியம்
    0.35
    डक्शन
    0.35
    POSITIVE LOGITS
     freedom
    1.22
     liberdade
    1.16
    自由に
    1.16
     свободы
    1.16
     libertad
    1.15
    自由
    1.14
     liberté
    1.10
     libertà
    1.10
     স্বাধীন
    1.09
    freedom
    1.07
    Activations Density 0.389%

    No Known Activations