© 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. 40362
    Prev
    Next
    INDEX
    Explanations

    track and tracking

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

    the neuron primarily detects numeric tokens—numbers, IDs, counts, and other digit sequences in the text.

    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
            
    -2.52
        
    -1.82
    鹟
    -1.78
     îles
    -1.73
           
    -1.71
    warzys
    -1.70
                        
    -1.68
    –
    -1.68
                                 
    -1.66
    </strong>
    -1.66
    POSITIVE LOGITS
     jätte
    2.16
    激情
    2.03
    щита
    2.03
     zijn
    2.02
    TRACK
    1.98
     organise
    1.95
    ==$
    1.95
    track
    1.95
     ľudí
    1.95
    ﮕ
    1.91
    Activations Density 0.032%

    No Known Activations