© 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. 60641
    Prev
    Next
    INDEX
    Explanations

    films starring actors

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

    The neuron fires most strongly on mentions of film cast—particularly actor and actress names (and related “starring” labels).

    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
     сцен
    -0.96
     актриса
    -0.96
     actress
    -0.89
    することに
    -0.85
    aporan
    -0.85
    ченные
    -0.82
    Actress
    -0.82
     akt
    -0.81
    getFull
    -0.80
     конструкция
    -0.77
    POSITIVE LOGITS
     protagonista
    0.97
     nicolas
    0.94
     protagonisti
    0.90
     NEWSLETTER
    0.86
    主角
    0.86
    यु
    0.85
     dafs
    0.84
     praticamente
    0.84
     Fb
    0.82
    leads
    0.81
    Activations Density 0.048%

    No Known Activations