© 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. 10-GEMMASCOPE-RES-131K
    7. 1511
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and prefixes

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

    The neuron flags mentions of polyhedral geometry terms (words like tetrahedron, octahedral, icosahedral, or “polytope”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ylase
    -1.90
    
    -1.89
    
    -1.73
     Gennaio
    -1.71
     Potencia
    -1.70
    ⎘
    -1.67
     väg
    -1.63
    letics
    -1.61
    ”？
    -1.61
     Luglio
    -1.60
    POSITIVE LOGITS
    "
    1.80
     vivimos
    1.73
     From
    1.68
     จาก
    1.66
    \
    1.61
    
    1.55
    .
    1.52
     hechas
    1.48
    狴
    1.45
     Both
    1.43
    Activations Density 0.007%

    No Known Activations