© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100300
    Prev
    Next
    INDEX
    Explanations

    groupId, Winchester, Tus

    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
    ⟞
    -2.95
    ൎ
    -2.42
    ſelves
    -2.36
    徕
    -2.28
     einer
    -2.27
     THE
    -2.27
    喾
    -2.25
    communist
    -2.22
     entendi
    -2.20
    ăzi
    -2.17
    POSITIVE LOGITS
    s
    3.27
    1
    3.02
    鱟
    2.56
    или
    2.50
    蒹
    2.47
     vengono
    2.41
     vermag
    2.39
    お疲れ
    2.38
     stiker
    2.34
     erhi
    2.31
    Activations Density 0.004%

    No Known Activations