© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4664
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and quotes

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

    The neuron strongly responds to tokens in highly structured, technical/spec‐list contexts—especially parameter names or numeric/value fields (e.g. bid amounts, “URL,” “SearchMaxCPC,” measurement terms) found in documentation or schema listings.

    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
    吣
    0.67
     जबरदस्त
    0.64
     кеңсеси
    0.63
     judíos
    0.63
    ujące
    0.63
    ímos
    0.61
    ರುತ್ತ
    0.60
    áním
    0.59
    ണ്ണ
    0.58
     carefree
    0.58
    POSITIVE LOGITS
            
    0.79
     (
    0.77
          
    0.76
     ;
    0.75
                    
    0.74
                            
    0.74
           
    0.73
                
    0.73
                                
    0.73
    0.73
    Activations Density 0.000%

    No Known Activations