© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1500
    Prev
    Next
    INDEX
    Explanations

    when leaving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    修复
    0.78
    iolipin
    0.75
    aspis
    0.73
     eradic
    0.71
     corrige
    0.70
    魇
    0.70
    aik
    0.70
    诵
    0.69
     बरामद
    0.69
     quét
    0.68
    POSITIVE LOGITS
     resigning
    2.47
     retirement
    2.36
     retiring
    2.35
     resign
    2.33
     retire
    2.32
     resignation
    2.29
     quitting
    2.26
     exit
    2.12
     retires
    2.08
    retirement
    2.08
    Activations Density 0.656%

    No Known Activations