© 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. 15961
    Prev
    Next
    INDEX
    Explanations

    mix

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

    the neuron detects numeric tokens with decimal points (floating-point numbers).

    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
    ↵
    0.85
     Parrish
    0.74
     Plenty
    0.70
    এ
    0.70
     Lower
    0.69
     Faster
    0.69
    ógrafo
    0.69
            
    0.69
                    
    0.66
         
    0.66
    POSITIVE LOGITS
    UMI
    0.77
     冖
    0.77
    диви
    0.77
     жерт
    0.75
     бъдат
    0.75
    ivne
    0.75
     necesit
    0.71
    egn
    0.71
    檛
    0.71
    clonal
    0.71
    Activations Density 0.000%

    No Known Activations