© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74612
    Prev
    Next
    INDEX
    Explanations

    stop action

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects occurrences of the word “stop,” especially when used as an imperative command to halt an action.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    又在
    -2.25
     但是
    -2.17
     
    -2.08
     kostenlose
    -1.97
    也在
    -1.96
    1
    -1.96
    '
    -1.92
    心灵
    -1.90
     所以
    -1.90
     that
    -1.88
    POSITIVE LOGITS
    ]
    2.50
    );
    2.47
    \%)
    2.25
    
    2.19
    ):
    2.17
     []
    2.08
     美人
    2.03
     télévisée
    2.03
    ]:
    2.02
    ;
    2.00
    Activations Density 0.010%

    No Known Activations