© 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. 103565
    Prev
    Next
    INDEX
    Explanations

    crew and cast information

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Carey
    -0.77
    Alguns
    -0.76
     Vad
    -0.76
    films
    -0.75
    jsoup
    -0.74
     films
    -0.74
    ेंद
    -0.72
     dishes
    -0.71
     عوض
    -0.70
     г
    -0.69
    POSITIVE LOGITS
    Crew
    1.16
     crew
    1.13
    keywords
    0.96
     Crew
    0.96
    crew
    0.94
    Keywords
    0.91
    Клю
    0.91
     cast
    0.88
     recomendación
    0.87
    キーワード
    0.86
    Activations Density 0.006%

    No Known Activations