© 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. 53-GEMMASCOPE-2-RES-262K
    7. 18654
    Prev
    Next
    INDEX
    Explanations

    tax

    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_53_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
     mixed
    0.41
     Mixed
    0.40
    uth
    0.37
    ician
    0.36
    ↵↵
    0.36
     Puro
    0.36
     Cep
    0.36
    ilda
    0.35
    ini
    0.35
     slow
    0.35
    POSITIVE LOGITS
     TAX
    0.53
    Tax
    0.50
     taxe
    0.49
     ট্যাক
    0.49
    tax
    0.49
    TAX
    0.49
    税
    0.48
     टैक्स
    0.46
     Sykes
    0.46
     taxon
    0.44
    Activations Density 0.000%

    No Known Activations