© 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. 15918
    Prev
    Next
    INDEX
    Explanations

    fill in, up, out

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

    fill, filling, filled

    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
    c
    0.68
    d
    0.54
    inburgh
    0.52
    b
    0.51
    et
    0.51
    v
    0.50
    biss
    0.49
    cenia
    0.48
     灬
    0.47
    رسی
    0.47
    POSITIVE LOGITS
     filling
    1.62
     Filling
    1.54
     Fill
    1.53
    Filling
    1.52
    Fill
    1.45
     fills
    1.45
    filling
    1.45
     запол
    1.42
     fill
    1.41
     FILL
    1.38
    Activations Density 0.405%

    No Known Activations