© 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. 116514
    Prev
    Next
    INDEX
    Explanations

    research, questions, or phrases like "YOUR CART"

    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
    спол
    -0.90
    jess
    -0.88
     كور
    -0.82
    beige
    -0.80
    blond
    -0.76
     będzie
    -0.76
     prevé
    -0.73
    ƶ
    -0.72
    AutoModerator
    -0.72
    をよく
    -0.70
    POSITIVE LOGITS
    forschung
    0.96
     research
    0.90
     novelty
    0.90
    пто
    0.84
     विश्लेषण
    0.81
     stieg
    0.81
    专家
    0.81
     basilica
    0.80
     informant
    0.79
    試合
    0.78
    Activations Density 0.008%

    No Known Activations