© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60816
    Prev
    Next
    INDEX
    Explanations

    words starting with eye

    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
    oplasts
    -0.82
    カリ
    -0.79
    faces
    -0.71
    DialogInterface
    -0.67
    cello
    -0.67
     yana
    -0.66
    绘
    -0.65
    racite
    -0.64
    ewear
    -0.64
    しが
    -0.63
    POSITIVE LOGITS
     eye
    1.27
     candy
    0.99
     catching
    0.91
     Eye
    0.90
    アイ
    0.85
     아이
    0.84
     Oxide
    0.84
    candy
    0.84
    catching
    0.84
     catch
    0.81
    Activations Density 0.019%

    No Known Activations