© 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. 49521
    Prev
    Next
    INDEX
    Explanations

    economic stimulus

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

    The neuron detects multi‐digit numeric tokens (i.e. numbers).

    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
    Improved
    -0.84
     Improvements
    -0.77
    improved
    -0.75
    posX
    -0.72
    seys
    -0.72
     zwing
    -0.72
    ificaciones
    -0.70
     Improved
    -0.70
     Reduction
    -0.69
    tems
    -0.69
    POSITIVE LOGITS
     stimulus
    2.83
     stimulate
    2.61
    Stim
    2.58
     stimul
    2.48
     stimulates
    2.38
     Stimulus
    2.34
    stim
    2.33
     stimulation
    2.31
     stimulating
    2.31
    stimulus
    2.20
    Activations Density 0.025%

    No Known Activations