© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25460
    Prev
    Next
    INDEX
    Explanations

    network setup and software

    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_22/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
    ]=\
    -1.14
    有些
    -0.93
      
    -0.91
     remainder
    -0.90
    趁
    -0.88
     we
    -0.86
     
    -0.86
    vč
    -0.84
     style
    -0.83
     Coleoptera
    -0.83
    POSITIVE LOGITS
    ᾿
    1.12
     颜色
    1.00
    ÁCT
    0.99
     标签
    0.96
     everyone
    0.96
     penghar
    0.93
     yako
    0.93
     功效
    0.92
     Официальный
    0.91
     ESTADO
    0.91
    Activations Density 0.245%

    No Known Activations