© 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. 22-GEMMASCOPE-RES-131K
    7. 92892
    Prev
    Next
    INDEX
    Explanations

    attributing or relating concepts and entities

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

    This neuron fires on verbs that express a relationship or comparison followed by a possessive pronoun and a noun (e.g. “compare my life to,” “places its faith in,” “attach importance to”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     prou
    -0.96
    вича
    -0.91
    Paco
    -0.90
     Hé
    -0.89
     Montagne
    -0.88
    nien
    -0.88
     regex
    -0.88
     Guarda
    -0.88
     Afrika
    -0.87
     Félix
    -0.87
    POSITIVE LOGITS
     ourselves
    1.08
     their
    1.07
    ってこと
    0.99
     myself
    0.96
     impresionantes
    0.92
     impresionante
    0.91
    terus
    0.91
     aleación
    0.91
    cribing
    0.90
    ioare
    0.89
    Activations Density 0.040%

    No Known Activations