© 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. 103424
    Prev
    Next
    INDEX
    Explanations

    bank

    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
     “
    -2.73
     欣赏
    -2.27
     Other
    -2.22
    缡
    -2.14
     ใน
    -2.14
    
    -2.09
    
    -1.98
     Also
    -1.92
    もありました
    -1.91
    躓
    -1.91
    POSITIVE LOGITS
    c
    2.84
    i
    2.69
    ｉ
    2.53
    ｄ
    2.42
    --
    2.31
    ('
    2.25
    This
    2.19
    is
    2.16
    ième
    2.11
    AddTagHelper
    2.09
    Activations Density 0.011%

    No Known Activations