© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67378
    Prev
    Next
    INDEX
    Explanations

    Walt Disney, Cats, red pill

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

    The neuron strongly activates on numerical tokens (digits or numbers, including decimals) 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_22/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
     Bardzo
    -0.98
     oraz
    -0.93
    erweise
    -0.92
     būt
    -0.91
     Są
    -0.91
     verlangt
    -0.90
    oznam
    -0.90
     subió
    -0.89
    
    -0.88
     Wszyst
    -0.88
    POSITIVE LOGITS
     sondern
    0.98
    Instead
    0.94
     instead
    0.92
    Ingredi
    0.89
    でしょうね
    0.88
     guarn
    0.86
    ths
    0.86
    different
    0.86
     disponibile
    0.84
     redi
    0.83
    Activations Density 0.137%

    No Known Activations