© 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. 22-GEMMASCOPE-RES-131K
    4. 28313
    Prev
    Next
    INDEX
    Explanations

    to specialized, our, the

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

    The neuron flags “to” in assignment/delegation‐style phrases—especially in passive constructions like “assigned to,” “delegated to,” or “entrusted 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
    d
    -1.24
     and
    -1.13
    
    -1.05
    J
    -1.05
     access
    -1.04
    t
    -1.02
    _
    -1.01
    ца
    -0.97
     zufolge
    -0.96
    nt
    -0.95
    POSITIVE LOGITS
     our
    1.55
    锨
    1.30
     devraient
    1.28
    tedy
    1.27
    Bisous
    1.27
    Síguenos
    1.25
    Liefs
    1.25
     someone
    1.25
     Apakah
    1.24
     you
    1.23
    Activations Density 0.027%

    No Known Activations