© 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. 31-GEMMASCOPE-2-RES-16K
    4. 378
    Prev
    Next
    INDEX
    Explanations

    possessive 's'

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

    The neuron fires specifically on the special beginning-of-sequence token.

    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_31_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
     
    0.70
      
    0.55
    new
    0.55
       
    0.54
    <
    0.52
        
    0.51
    1
    0.48
    ↵
    0.48
    L
    0.46
    2
    0.46
    POSITIVE LOGITS
     Gründe
    0.55
     अल्को
    0.54
     Flüss
    0.54
     أفضل
    0.54
     सूत्रकृ
    0.54
    <unused619>
    0.53
     Foire
    0.53
     आरमारा
    0.53
     Geräte
    0.52
     Fokus
    0.52
    Activations Density 0.011%

    No Known Activations