© 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-262K
    7. 137214
    Prev
    Next
    INDEX
    Explanations

    spacing, gap, separation

    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_262k_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
     انتہائی
    0.44
    dims
    0.40
     geniş
    0.40
    癱
    0.40
     Сьогодні
    0.40
    interests
    0.39
     اتھار
    0.39
    UVW
    0.38
    {|\
    0.38
    꽉
    0.38
    POSITIVE LOGITS
    Spacing
    0.87
     spacing
    0.85
     spacer
    0.85
     Spacer
    0.83
     spacers
    0.80
     separation
    0.79
     Abstand
    0.79
     Separation
    0.77
     gap
    0.71
     distancing
    0.71
    Activations Density 0.025%

    No Known Activations