© 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. 22-GEMMASCOPE-RES-131K
    7. 65280
    Prev
    Next
    INDEX
    Explanations

    math and code delimiters

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

    The neuron strongly responds to multi‐digit numeric tokens (i.e. numbers of two or more digits).

    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
     which
    -1.02
     this
    -0.99
     Which
    -0.99
     it
    -0.98
    ˝
    -0.98
    
    -0.96
     می‌
    -0.94
     the
    -0.94
    、“
    -0.94
    ˛
    -0.93
    POSITIVE LOGITS
    ptian
    1.02
    ㆁ
    1.02
    髌
    1.00
    𝕿
    1.00
     kroppen
    0.99
    üte
    0.99
     guarante
    0.99
    ंत्र
    0.98
     rostro
    0.97
     actualizada
    0.97
    Activations Density 0.055%

    No Known Activations