© 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. 39568
    Prev
    Next
    INDEX
    Explanations

    acting and interim roles

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

    The neuron activates on mentions of temporary or interim appointments—specifically on the words “acting” and “interim” (and their adjacent titles).

    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
    쉘
    -1.41
     géographie
    -1.30
    intéress
    -1.30
    鷂
    -1.27
    こん
    -1.26
     Fähigkeit
    -1.24
    
    -1.24
     respective
    -1.24
     dochter
    -1.24
     ausgewä
    -1.23
    POSITIVE LOGITS
    ?"
    1.57
     has
    1.42
    out
    1.42
     in
    1.35
     seems
    1.34
    ed
    1.31
     interim
    1.28
     at
    1.26
     have
    1.26
     because
    1.24
    Activations Density 0.010%

    No Known Activations