© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 137765
    Prev
    Next
    INDEX
    Explanations

    tub and variations

    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_16_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
    is
    1.00
    ه
    0.96
    ის
    0.91
    ية
    0.86
     déi
    0.82
     لي
    0.79
     цю
    0.79
     by
    0.79
    ၎
    0.78
     jeu
    0.77
    POSITIVE LOGITS
     tubs
    1.27
    tub
    1.21
     tub
    1.10
    v
    1.05
    eli
    1.02
    रा
    0.96
    Tub
    0.95
    م
    0.92
    m
    0.90
     adhesives
    0.90
    Activations Density 0.001%

    No Known Activations