© 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. 43170
    Prev
    Next
    INDEX
    Explanations

    rebate, rebase, abatement

    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
     сказал
    -2.56
    擱
    -2.48
    iocene
    -2.42
    
    -2.39
    ⸫
    -2.34
    轳
    -2.33
    ⚢
    -2.33
    ⚊
    -2.33
    숑
    -2.30
    และ
    -2.22
    POSITIVE LOGITS
     
    2.73
    ↵
    2.56
     gedurende
    2.36
     çoğu
    2.19
     murieron
    2.14
    ,…
    2.05
    Cuándo
    2.03
     particularly
    2.03
     naast
    1.99
     obecnie
    1.98
    Activations Density 0.002%

    No Known Activations