© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8980
    Prev
    Next
    INDEX
    Explanations

    roles and relationships

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

    This neuron activates strongly on words that denote personal relationships or social roles (e.g., kinship terms, titles, and roles).

    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
     is
    -2.31
     of
    -1.68
     pierws
    -1.52
     trente
    -1.47
     trzec
    -1.44
     zwanzig
    -1.43
    :
    -1.35
     onderdeel
    -1.34
     moeite
    -1.33
     marbre
    -1.29
    POSITIVE LOGITS
     any
    1.73
     all
    1.64
     so
    1.63
    Ÿ
    1.56
     continued
    1.45
     Since
    1.38
    zembro
    1.36
     when
    1.36
     now
    1.35
    }
    
    1.34
    Activations Density 0.080%

    No Known Activations