© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14037
    Prev
    Next
    INDEX
    Explanations

    influencing, perceived, accusing, helper, properly, fueled

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

    The neuron fires most strongly on the last substantive token before the end of each text segment, effectively marking segment boundaries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    							
    0.84
    ;
    0.84
    					
    0.84
    			
    0.83
    0
    0.75
    				
    0.75
     Flour
    0.72
     ਵਿ
    0.70
     সংলাপ
    0.70
     экрана
    0.69
    POSITIVE LOGITS
    ઙ
    0.88
     donnent
    0.87
    ीण
    0.85
    infile
    0.85
     voluto
    0.80
    कांनी
    0.77
    ्मण
    0.77
    ாதீர்கள்
    0.76
    inie
    0.75
    णाची
    0.75
    Activations Density 0.000%

    No Known Activations