© 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. 72152
    Prev
    Next
    INDEX
    Explanations

    specific acronyms and terms

    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
    0
    -3.16
    峩
    -2.75
     jezt
    -2.69
    ⽼
    -2.64
    笵
    -2.63
    囖
    -2.63
    ཋ
    -2.58
    -
    -2.56
    \_
    -2.55
    寕
    -2.52
    POSITIVE LOGITS
    。“
    2.88
     selben
    2.78
    ，“
    2.52
    菔
    2.47
    ᨆ
    2.45
    餮
    2.42
    
    2.38
    ),
    2.36
    ",
    2.34
    k
    2.34
    Activations Density 0.023%

    No Known Activations