© 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. 101138
    Prev
    Next
    INDEX
    Explanations

    words ending in ium

    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
    8
    -3.61
    5
    -3.61
    6
    -3.58
    7
    -3.42
    0
    -3.36
    栳
    -3.13
    
    -2.94
    1
    -2.94
    3
    -2.88
    2
    -2.83
    POSITIVE LOGITS
    最重要的
    3.66
    
    3.03
    呖
    2.84
    ’
    2.61
    s
    2.55
    踅
    2.48
    漚
    2.45
     It
    2.44
     otras
    2.42
     принято
    2.42
    Activations Density 0.031%

    No Known Activations