© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9171
    Prev
    Next
    INDEX
    Explanations

    often contradictory

    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_13_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
     lipoproteins
    1.61
     puns
    1.45
    apanicola
    1.44
     SMTP
    1.41
    ingt
    1.39
    ,</
    1.38
    ington
    1.37
     smtp
    1.37
     turnout
    1.36
     drawdown
    1.36
    POSITIVE LOGITS
    了
    1.18
    ly
    1.08
    ผู้
    1.08
    籟
    1.07
    씌
    1.06
    ボリー
    1.04
    家の
    1.02
    主动
    1.01
     من
    1.00
     dai
    1.00
    Activations Density 0.087%

    No Known Activations