© 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. 11891
    Prev
    Next
    INDEX
    Explanations

    events and dates

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

    start, began, next, first, last

    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
    ळून
    0.42
    uştur
    0.39
    ://$
    0.39
    eté
    0.39
    స్తు
    0.39
    會有
    0.38
    కుండా
    0.38
    趸
    0.37
    zigen
    0.37
    ትር
    0.36
    POSITIVE LOGITS
     began
    0.94
     dates
    0.93
     commenced
    0.91
     dated
    0.91
     fecha
    0.87
    เริ่ม
    0.87
     started
    0.87
    开始
    0.87
     begun
    0.87
     date
    0.80
    Activations Density 0.654%

    No Known Activations