© 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. 102612
    Prev
    Next
    INDEX
    Explanations

    visual patterns and designs

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

    The neuron activates on imperative or procedural step language—i.e. words and punctuation signaling instructions or step‐by‐step directions in a how-to tutorial.

    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
    dims
    -0.84
    ensión
    -0.83
    comy
    -0.81
     thưởng
    -0.79
    ioka
    -0.77
    レンダー
    -0.77
     выход
    -0.76
     validation
    -0.76
     refaire
    -0.75
     labi
    -0.74
    POSITIVE LOGITS
     striped
    1.43
     stripes
    1.39
     floral
    1.28
     checker
    1.27
     camouflage
    1.24
     gradient
    1.24
     leopard
    1.16
     stripe
    1.15
    渐变
    1.14
     marble
    1.13
    Activations Density 0.074%

    No Known Activations