© 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. 10-GEMMASCOPE-RES-131K
    4. 90650
    Prev
    Next
    INDEX
    Explanations

    parentheses annotations

    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
     
    -2.19
     utterly
    -1.78
     excessive
    -1.77
    J
    -1.76
     only
    -1.73
     also
    -1.71
    W
    -1.70
     undeniably
    -1.70
    R
    -1.70
     enormous
    -1.68
    POSITIVE LOGITS
    矬
    2.39
    螃
    2.20
    
    2.03
    ⎘
    2.00
    during
    1.98
     kiedy
    1.88
     quando
    1.87
    
    1.86
     WHEN
    1.86
    屨
    1.85
    Activations Density 0.036%

    No Known Activations