© 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-262K
    7. 12376
    Prev
    Next
    INDEX
    Explanations

    time until an event

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

    until

    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_262k_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
     was
    0.80
    。
    0.74
     ו
    0.71
    ä
    0.68
     and
    0.68
    ли
    0.66
    i
    0.66
     و
    0.65
     व
    0.64
    ஸ்
    0.64
    POSITIVE LOGITS
     Until
    0.78
    Until
    0.77
    until
    0.71
    September
    0.66
    1
    0.66
     ድረስ
    0.63
    ok
    0.62
    고
    0.62
    Autumn
    0.61
    有一天
    0.61
    Activations Density 0.048%

    No Known Activations