© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8515
    Prev
    Next
    INDEX
    Explanations

    observatory and worldly concepts

    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
     流れ
    -2.88
    怿
    -2.67
    CHREIB
    -2.66
    珧
    -2.66
    
    -2.56
    M
    -2.56
    注意事
    -2.55
    的身体
    -2.55
     captivating
    -2.53
    搋
    -2.52
    POSITIVE LOGITS
     This
    2.92
     While
    2.80
    )
    2.72
     {
    2.56
     get
    2.55
    .....
    2.45
     Having
    2.42
     At
    2.38
     Unlike
    2.36
     Although
    2.34
    Activations Density 0.004%

    No Known Activations