© 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. 42755
    Prev
    Next
    INDEX
    Explanations

    Adrian followed by surname

    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
    籥
    -2.75
    —
    -2.63
    в
    -2.55
     of
    -2.53
     neuen
    -2.48
     owing
    -2.45
     Of
    -2.45
    ネイル
    -2.42
    ⑉
    -2.36
     Their
    -2.34
    POSITIVE LOGITS
    硨
    3.22
    狆
    3.20
    ଃ
    2.70
    ?");
    2.67
     aussit
    2.64
    ⾄
    2.59
    
    2.58
     вспомина
    2.56
     hii
    2.56
     tyd
    2.56
    Activations Density 0.006%

    No Known Activations