© 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. 1412
    Prev
    Next
    INDEX
    Explanations

    actor

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

    The neuron fires strongly on occurrences of the word “actor” (and its plural “actors”).

    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
    ’
    -2.30
    的大
    -2.08
    uellement
    -2.02
    ⇘
    -2.02
    りました
    -2.02
    ších
    -1.84
    ŚĆ
    -1.82
    rocław
    -1.77
    ίας
    -1.77
    ませんが
    -1.76
    POSITIVE LOGITS
    .
    2.38
     you
    2.30
    檮
    2.27
    ',
    
    2.22
    𖥧
    2.19
    </em>
    2.14
    肫
    2.11
     tornar
    2.09
     ilumina
    2.08
     wilden
    2.02
    Activations Density 0.012%

    No Known Activations