© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84772
    Prev
    Next
    INDEX
    Explanations

    church names

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

    The neuron strongly activates on numeric tokens and quantities (e.g. table values, percentages, years, counts).

    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
    用户名
    -0.78
    ضور
    -0.71
    Minneapolis
    -0.68
     via
    -0.67
    南瓜
    -0.66
    Maxi
    -0.66
     Controversy
    -0.65
    ėk
    -0.64
    Deja
    -0.64
    ặt
    -0.63
    POSITIVE LOGITS
     rounding
    1.10
     cells
    0.90
    cell
    0.89
     Rounds
    0.88
    オリティ
    0.84
     reliability
    0.84
    cells
    0.83
    interpre
    0.83
    tries
    0.83
     azy
    0.83
    Activations Density 0.009%

    No Known Activations