© 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. 102783
    Prev
    Next
    INDEX
    Explanations

    first sequences or remakes

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

    The neuron strongly activates on film‐production and sequel announcements—i.e. jargon and details about making or shooting movies.

    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
     aktif
    -0.93
    Facilit
    -0.89
     فعال
    -0.85
    фин
    -0.84
     tersangka
    -0.80
    对其
    -0.80
    ြ
    -0.79
    我怎么
    -0.79
    Zalety
    -0.78
    𝑿
    -0.78
    POSITIVE LOGITS
     shown
    1.00
     director
    0.98
     screenplay
    0.97
     sequences
    0.91
     situational
    0.87
     logic
    0.87
     mass
    0.82
     Greyhound
    0.81
    umbing
    0.80
    逻辑
    0.80
    Activations Density 0.019%

    No Known Activations