© 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. 32576
    Prev
    Next
    INDEX
    Explanations

    maintaining a state

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

    The neuron is primarily detecting multi‐digit numerical values (quantitative data) 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
     lección
    -0.86
     acepción
    -0.86
    liyor
    -0.82
     aggiungere
    -0.80
     fornece
    -0.79
    ligere
    -0.79
    onite
    -0.79
     asuntos
    -0.78
     óculos
    -0.78
     propietarios
    -0.77
    POSITIVE LOGITS
     maintain
    6.47
     maintaining
    5.81
     maintained
    5.56
     maintains
    5.41
    maintain
    5.34
    Maintain
    5.25
     Maintain
    5.16
    Maintaining
    4.97
     Maintaining
    4.72
    保持
    4.44
    Activations Density 0.349%

    No Known Activations