© 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. 34-GEMMASCOPE-RES-131K
    7. 49735
    Prev
    Next
    INDEX
    Explanations

    doing tasks

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

    The neuron strongly activates on numeric tokens (integer numbers) 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_34/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
     gelungen
    -0.91
    umumkan
    -0.91
    vertida
    -0.87
     également
    -0.86
     dobra
    -0.86
     mereka
    -0.85
    єте
    -0.85
    )_{
    -0.84
    egl
    -0.83
    一起去
    -0.82
    POSITIVE LOGITS
     doing
    2.30
     adding
    2.20
     removing
    2.05
     installing
    1.99
     việc
    1.99
     accessing
    1.87
     choosing
    1.84
     owning
    1.83
     putting
    1.83
     buying
    1.80
    Activations Density 0.215%

    No Known Activations