© 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. 22-GEMMASCOPE-RES-131K
    7. 35023
    Prev
    Next
    INDEX
    Explanations

    subjective postural vertical

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

    The neuron strongly activates on numeric tokens (integers, decimals, counts, measurements, etc.).

    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
    мери
    -0.96
     MaterialApp
    -0.95
     étr
    -0.94
     meninggalkan
    -0.91
     czeka
    -0.90
     autocollant
    -0.90
    itori
    -0.88
    minus
    -0.87
    only
    -0.87
     entraî
    -0.86
    POSITIVE LOGITS
     Sociale
    1.01
    块钱
    0.95
    StateException
    0.89
     endom
    0.88
     lampada
    0.85
    synchronize
    0.84
    ApplicationTests
    0.84
     mening
    0.83
     centrif
    0.83
     grazed
    0.82
    Activations Density 0.086%

    No Known Activations