© 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. 38110
    Prev
    Next
    INDEX
    Explanations

    fill

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

    padding or filling to a length

    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
     paroles
    0.45
     abgesch
    0.45
     aigu
    0.42
     vaiht
    0.42
     ruptura
    0.42
     alternativ
    0.41
     histology
    0.40
    癬
    0.40
     enumerable
    0.40
     animasi
    0.40
    POSITIVE LOGITS
     부족
    0.93
    Fill
    0.87
    补
    0.83
    fill
    0.81
    不足
    0.80
    足り
    0.79
     недоста
    0.78
     fill
    0.77
    补充
    0.77
     Fill
    0.74
    Activations Density 0.042%

    No Known Activations