© 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. 49308
    Prev
    Next
    INDEX
    Explanations

    plug housing

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

    The neuron fires most strongly on tokens containing digits (e.g. years, numbers, numeric identifiers).

    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
    æn
    -0.79
    mischer
    -0.77
    пети
    -0.75
    mmung
    -0.75
    Type
    -0.75
    BLES
    -0.73
    Beijo
    -0.73
     sah
    -0.72
    Abraços
    -0.72
    topf
    -0.71
    POSITIVE LOGITS
    melan
    0.84
     here
    0.82
     zeigt
    0.74
    amanda
    0.73
     Anja
    0.71
     visible
    0.70
     име
    0.69
    鋒
    0.69
     別
    0.69
    kaos
    0.69
    Activations Density 0.020%

    No Known Activations