© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11613
    Prev
    Next
    INDEX
    Explanations

    Value Added Tax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    𝚊
    2.14
    beeld
    2.11
    奕
    2.02
    eram
    2.01
    𝚎
    2.00
    𝚖
    1.99
    Logs
    1.97
    ﮩ
    1.96
    ющимся
    1.94
    𝚜
    1.88
    POSITIVE LOGITS
     seized
    1.73
     ric
    1.64
     cue
    1.63
     infused
    1.63
     IMPORT
    1.62
     inc
    1.62
     PAST
    1.61
     estr
    1.60
     markup
    1.58
     introductions
    1.56
    Activations Density 0.031%

    No Known Activations