© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10560
    Prev
    Next
    INDEX
    Explanations

    stopping or pausing

    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_22_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
     طلع
    0.99
    ܘ
    0.87
     removals
    0.83
    worthiness
    0.82
     removal
    0.80
     Lowe
    0.80
     castles
    0.79
    ⇐
    0.79
    لول
    0.78
     demolition
    0.78
    POSITIVE LOGITS
     stopped
    1.94
     halted
    1.90
     paused
    1.89
     stop
    1.84
     pausing
    1.79
     stopping
    1.75
    停止
    1.74
    暂停
    1.73
     stops
    1.71
     pause
    1.71
    Activations Density 0.294%

    No Known Activations