© 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. 15063
    Prev
    Next
    INDEX
    Explanations

    until something happens

    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_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
    。
    0.84
    ли
    0.72
    ে
    0.70
    i
    0.69
     was
    0.68
    e
    0.64
     کیسینو
    0.61
     périodes
    0.60
     warranty
    0.59
    。【
    0.59
    POSITIVE LOGITS
    Until
    1.16
     Until
    1.10
    until
    1.01
    直到
    0.89
     until
    0.86
     ድረስ
    0.85
    直至
    0.80
    1
    0.79
    Hasta
    0.77
    Till
    0.72
    Activations Density 1.237%

    No Known Activations