© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93641
    Prev
    Next
    INDEX
    Explanations

    by the

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

    The neuron strongly activates on occurrences of the bigram “by the.”

    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
    -0.89
     pasto
    -0.86
    苅
    -0.84
    ţ
    -0.81
    局面
    -0.81
    ț
    -0.80
    Itu
    -0.79
    期间
    -0.78
     lige
    -0.77
     balón
    -0.75
    POSITIVE LOGITS
     grace
    1.66
     Grace
    1.41
     looks
    1.37
     standards
    1.33
     same
    1.26
    Grace
    1.23
     end
    1.23
     sounds
    1.21
     time
    1.15
    grace
    1.13
    Activations Density 0.043%

    No Known Activations