© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72914
    Prev
    Next
    INDEX
    Explanations

    beneficiary or discharge

    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
     可以
    -2.81
    麼
    -2.66
    頹
    -2.55
    褔
    -2.53
     แต่
    -2.47
    情況
    -2.45
    飆
    -2.39
     budú
    -2.38
    ﻞ
    -2.38
    indor
    -2.34
    POSITIVE LOGITS
    h
    3.31
    ri
    3.03
    𓆜
    3.02
    趼
    2.92
     
    2.92
    ’
    2.78
    y
    2.73
    ⟞
    2.64
    芣
    2.53
    </strong>
    2.50
    Activations Density 0.007%

    No Known Activations