© 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. 10-GEMMASCOPE-RES-131K
    4. 130412
    Prev
    Next
    INDEX
    Explanations

    Chief and titles

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

    The neuron detects occurrences of the word “Chief” (used as a title or role designation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -3.95
    ."
    -3.06
    ?
    -2.44
     traditionellen
    -2.36
    师父
    -2.28
     aqueles
    -2.27
    ";
    -2.27
     
    -2.20
     wenige
    -2.17
     berühmten
    -2.17
    POSITIVE LOGITS
     zoude
    3.09
    ’,
    2.98
     damen
    2.92
     paura
    2.80
    most
    2.75
    泺
    2.73
     mosso
    2.73
     rajut
    2.70
     animato
    2.70
     affez
    2.69
    Activations Density 0.009%

    No Known Activations