© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89957
    Prev
    Next
    INDEX
    Explanations

    filmmaking and directing

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

    The neuron flags descriptive film‐review language—words that talk about cinematic style, genre, editing, and production elements.

    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
    𝛽
    -1.02
    andia
    -0.98
    inada
    -0.94
    㗎
    -0.94
    daille
    -0.93
     beleid
    -0.92
     siitä
    -0.91
    istique
    -0.91
    genes
    -0.91
     ponownie
    -0.91
    POSITIVE LOGITS
     film
    1.66
     camera
    1.49
     shots
    1.43
     films
    1.42
     filmed
    1.40
     shot
    1.38
     director
    1.36
     directors
    1.30
     filming
    1.29
     filmmakers
    1.28
    Activations Density 0.026%

    No Known Activations