© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51043
    Prev
    Next
    INDEX
    Explanations

    filling or filled spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    горь
    0.45
     выпа
    0.35
    astrous
    0.35
     రే
    0.34
    quera
    0.34
     Yo
    0.34
    訸
    0.34
    ançon
    0.34
    寡
    0.34
     Blades
    0.33
    POSITIVE LOGITS
     filling
    2.80
     fill
    2.69
     запол
    2.66
     fills
    2.59
     filled
    2.53
    Filling
    2.50
     Filling
    2.48
     Fill
    2.44
     wypeł
    2.41
    Fill
    2.39
    Activations Density 0.150%

    No Known Activations