© 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. 4232
    Prev
    Next
    INDEX
    Explanations

    classification or equivalence

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

    The neuron detects copular constructions (forms of “be” plus a predicate) that classify or define the subject (e.g. “are deemed employees,” “be treated as cash advance,” “considered to be a disability”).

    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
     ня
    -0.79
    после
    -0.79
    chukwu
    -0.78
     emociones
    -0.78
     aucune
    -0.75
    ichia
    -0.74
    뿜
    -0.74
     tắt
    -0.73
     Rettung
    -0.73
    heast
    -0.73
    POSITIVE LOGITS
     "
    1.58
     “
    1.36
     '
    1.20
    立派
    1.14
     equivalent
    1.12
     „
    1.10
     "'
    1.02
     ‘
    1.01
    equivalent
    0.96
     ‘‘
    0.96
    Activations Density 0.080%

    No Known Activations