© 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. 98766
    Prev
    Next
    INDEX
    Explanations

    the role of mum

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

    The neuron triggers on words denoting personal social or familial roles and relationships.

    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
     придется
    -1.29
    Characterization
    -1.21
    ർ
    -1.20
    ครับ
    -1.18
    啻
    -1.14
     "[
    -1.06
     flavorful
    -1.06
     characterizing
    -1.04
    ii
    -1.00
     realized
    -1.00
    POSITIVE LOGITS
    Whilst
    1.93
     whilst
    1.90
     Whilst
    1.85
    ilisation
    1.02
     envisage
    0.99
    Firstly
    0.98
     firstly
    0.97
     pretence
    0.95
    wnież
    0.94
    ůj
    0.94
    Activations Density 0.134%

    No Known Activations