© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45609
    Prev
    Next
    INDEX
    Explanations

    states of deficiency

    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
    Negative Logits
     Dritten
    -2.95
    I
    -2.58
    老太太
    -2.56
     Allgemeinen
    -2.55
     dritten
    -2.48
    acamole
    -2.48
     Zweiten
    -2.45
    价格
    -2.45
     vorigen
    -2.42
     Ersten
    -2.41
    POSITIVE LOGITS
    潆
    3.16
    踅
    2.66
    趼
    2.52
    はその
    2.47
    Oft
    2.45
    驁
    2.42
    ‪.‬‬
    2.28
    はお
    2.25
     यदि
    2.22
    Chances
    2.22
    Activations Density 0.009%

    No Known Activations