© 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. 110888
    Prev
    Next
    INDEX
    Explanations

    promoting and facilitating actions

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

    The neuron activates on formal, high-level action verbs that describe objectives or processes (e.g. promote, facilitate, enhance) in academic, policy, or research-proposal style text.

    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
     firstly
    -1.55
     estremamente
    -1.44
     hoặc
    -1.40
     сначала
    -1.33
     یا
    -1.30
     caracteriza
    -1.22
    はもちろん
    -1.21
     nejen
    -1.19
     merece
    -1.17
     pedimos
    -1.13
    POSITIVE LOGITS
     вообще
    1.66
     overall
    1.66
     überhaupt
    1.39
    overall
    1.38
     Overall
    1.37
    อื่น
    1.27
     to
    1.23
     vůbec
    1.12
     outras
    1.12
    astă
    1.09
    Activations Density 0.274%

    No Known Activations