© 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. 66254
    Prev
    Next
    INDEX
    Explanations

    location and relation

    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
     byen
    -1.17
     både
    -1.08
     ulike
    -1.05
     сверху
    -1.00
     terke
    -1.00
     galinha
    -0.98
    上から
    -0.92
    عالی
    -0.92
    ligen
    -0.92
     çelik
    -0.91
    POSITIVE LOGITS
     near
    4.13
    near
    2.69
     beside
    2.48
     next
    2.39
    Near
    2.25
     behind
    2.23
     Near
    2.11
     by
    2.08
     près
    1.98
     gần
    1.84
    Activations Density 0.039%

    No Known Activations