© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63630
    Prev
    Next
    INDEX
    Explanations

    movie titles

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

    The neuron strongly activates on proper names—especially movie titles and film‐industry entities (and their connecting prepositions) in the 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
    襞
    -0.71
     unconsciously
    -0.68
     faint
    -0.66
     stopped
    -0.66
     boiling
    -0.66
     combining
    -0.65
    生的
    -0.65
     consistently
    -0.65
    maketitle
    -0.64
    麴
    -0.64
    POSITIVE LOGITS
    Maze
    0.94
     Maze
    0.93
     Allied
    0.92
     Venom
    0.90
     GONZ
    0.89
     Dunk
    0.83
    MAR
    0.80
    Dunk
    0.79
    kuu
    0.79
    Thor
    0.78
    Activations Density 0.033%

    No Known Activations