© 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. 34-GEMMASCOPE-RES-131K
    4. 32990
    Prev
    Next
    INDEX
    Explanations

    academies and their fields

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

    The neuron strongly activates on references to formal institutions—especially academic bodies (e.g. “Academy of Sciences,” “Royal Institute,” 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
    إنه
    -0.86
    計
    -0.84
    GIN
    -0.82
    ügen
    -0.82
    zzano
    -0.79
    льников
    -0.76
    idual
    -0.76
     бампер
    -0.75
    legen
    -0.75
    untura
    -0.74
    POSITIVE LOGITS
     Claudia
    0.68
     schönen
    0.67
    ostomy
    0.67
     fine
    0.67
     refreshing
    0.66
     proved
    0.66
    riculture
    0.66
    oltà
    0.66
     Fine
    0.65
    beros
    0.65
    Activations Density 0.054%

    No Known Activations