© 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. 53-GEMMASCOPE-2-RES-65K
    7. 6754
    Prev
    Next
    INDEX
    Explanations

    root phrases and collocations

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

    root cause

    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_53_width_65k_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
    逾
    0.42
    覦
    0.42
     honed
    0.41
    ිය
    0.40
    jego
    0.40
     çizg
    0.39
    鷗
    0.39
    جل
    0.39
    हूं
    0.39
     expiring
    0.38
    POSITIVE LOGITS
     Root
    0.98
     root
    0.96
    root
    0.92
    Root
    0.90
     뿌
    0.88
     ROOT
    0.81
     Roots
    0.78
     جذر
    0.75
     الجذر
    0.75
     Wurzel
    0.74
    Activations Density 0.011%

    No Known Activations