© 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. 33397
    Prev
    Next
    INDEX
    Explanations

    diagrams and plots

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

    The neuron detects procedural descriptions of mathematical methods or steps (e.g. references to “simple method,” “set theory,” drawing Venn diagrams, etc.)

    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
     clutched
    -0.75
    hamed
    -0.74
    baş
    -0.70
    Oops
    -0.70
    woke
    -0.69
    greedy
    -0.69
    reserva
    -0.68
     polymorphic
    -0.67
    Dys
    -0.66
    kubectl
    -0.65
    POSITIVE LOGITS
     Venn
    2.50
     venn
    1.83
     ROC
    1.34
     Gantt
    1.20
     dend
    1.19
     spider
    1.16
    ven
    1.12
     scatter
    1.09
    ROC
    1.06
     Feynman
    1.04
    Activations Density 0.103%

    No Known Activations