© 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. 2504
    Prev
    Next
    INDEX
    Explanations

    be + adjective

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

    The neuron fires on occurrences of the verb “to be” (including its inflected forms like “be,” “being,” 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
     behar
    -1.01
    fohlen
    -1.00
    sibility
    -1.00
    strahlung
    -0.98
    풍
    -0.94
    ability
    -0.93
    стями
    -0.93
     ideen
    -0.91
    стям
    -0.90
     manuelle
    -0.90
    POSITIVE LOGITS
     careful
    1.80
     proactive
    1.55
     generous
    1.38
     diligent
    1.34
     selective
    1.34
     aggressive
    1.32
     explicit
    1.28
     cautious
    1.27
     clever
    1.27
     gentle
    1.22
    Activations Density 0.059%

    No Known Activations