© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111734
    Prev
    Next
    INDEX
    Explanations

    offering help or solutions

    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_10/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
    䊳
    -1.50
     assust
    -1.42
    .}(
    -1.42
    なー
    -1.41
    趿
    -1.41
    媖
    -1.40
    蠓
    -1.39
    僦
    -1.39
     aceit
    -1.38
    desertcart
    -1.38
    POSITIVE LOGITS
    ↵↵
    1.78
    >
    1.72
    [
    1.46
    0
    1.45
    =
    1.44
     Eropa
    1.43
     Sabtu
    1.41
     findest
    1.41
     Gubernur
    1.41
     wisata
    1.40
    Activations Density 0.016%

    No Known Activations