© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 896
    Prev
    Next
    INDEX
    Explanations

    financial and technical terms

    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
     Assim
    1.14
    ,
    1.11
     and
    1.09
    ,/
    1.08
     envelope
    1.08
     wall
    1.06
     Essas
    1.06
     raindrops
    1.05
     escape
    1.05
     Esses
    1.02
    POSITIVE LOGITS
    本部
    1.62
    ripción
    1.55
    期限
    1.42
    nički
    1.42
    Фі
    1.42
    坟
    1.39
    投标文件
    1.37
    無需簽證
    1.37
    شنا
    1.36
    絽
    1.35
    Activations Density 5.692%

    No Known Activations