© 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. 53-GEMMASCOPE-2-RES-65K
    7. 2964
    Prev
    Next
    INDEX
    Explanations

    Greek words and endings

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

    Spanish and Greek word endings

    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_53_width_65k_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
    ÉT
    0.47
    ÁN
    0.46
    َنْ
    0.43
    ாம்
    0.43
     commandments
    0.42
     வண்ணப்பூ
    0.42
    ρών
    0.41
    ീകരണ
    0.41
     वार्
    0.41
    \`
    0.41
    POSITIVE LOGITS
    ματα
    0.70
    σεις
    0.69
    ματος
    0.66
    ψει
    0.64
    σεων
    0.62
    σιμο
    0.60
    ωση
    0.60
    θεση
    0.59
    θηκε
    0.59
    ωσε
    0.57
    Activations Density 0.010%

    No Known Activations