© 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. 49036
    Prev
    Next
    INDEX
    Explanations

    or after, or before, or about

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

    The neuron flags standalone numeric tokens (numbers composed of digits).

    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
     Kyrgyzstan
    -0.79
     pinky
    -0.73
     endo
    -0.72
    ietic
    -0.70
     Flas
    -0.69
     sesuatu
    -0.68
     creeks
    -0.68
     Ghanaians
    -0.68
     Shal
    -0.67
     (*(
    -0.67
    POSITIVE LOGITS
     देश
    0.67
    漱
    0.67
    Breakdown
    0.67
     interest
    0.66
    Presenter
    0.66
    궤
    0.65
    чиком
    0.64
    нович
    0.64
    cor
    0.63
    orks
    0.63
    Activations Density 0.066%

    No Known Activations