© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22273
    Prev
    Next
    INDEX
    Explanations

    five

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

    The neuron specifically detects the spelled-out number “Five.”

    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
    ↵↵
    -4.31
    1
    -4.31
    U
    -3.94
    E
    -3.86
    F
    -3.84
    “
    -3.83
    B
    -3.81
    4
    -3.70
     
    -3.56
    D
    -3.52
    POSITIVE LOGITS
     शुर
    3.75
     That
    3.61
     There
    3.20
     Surprisingly
    3.08
     phénom
    2.98
    ！"
    2.98
     और
    2.91
    
    2.89
    埸
    2.88
    琹
    2.88
    Activations Density 0.016%

    No Known Activations