© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13048
    Prev
    Next
    INDEX
    Explanations

    day

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

    numbered days

    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
    ל
    0.72
    ↵
    0.68
    સ
    0.67
     monthly
    0.62
     halftime
    0.62
        
    0.59
    Các
    0.59
    त
    0.59
     quarterly
    0.58
     lage
    0.58
    POSITIVE LOGITS
     päev
    1.02
    一日
    0.99
    day
    0.98
     день
    0.97
     day
    0.94
     दिन
    0.94
     giornata
    0.87
     dzień
    0.86
    날
    0.86
     giorno
    0.85
    Activations Density 0.363%

    No Known Activations