© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29150
    Prev
    Next
    INDEX
    Explanations

    correspondence and bijection

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

    The neuron spotlights mathematical‐function terminology—words that describe mappings or correspondences (e.g. map, mapping, one-to-one, correspondence, bijection, injective).

    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
    脔
    -1.75
    Kings
    -1.38
     ventilación
    -1.38
    我們
    -1.34
    
    -1.30
    𖧵
    -1.30
    Queensland
    -1.28
    👨
    -1.25
     alebo
    -1.24
     podczas
    -1.24
    POSITIVE LOGITS
     coincident
    1.66
    '
    1.60
     Конечно
    1.50
    」,
    1.49
    <td>
    1.45
    داً
    1.45
    」(
    1.41
     pleasing
    1.41
     otros
    1.41
     Она
    1.40
    Activations Density 0.041%

    No Known Activations