© 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. 34-GEMMASCOPE-RES-131K
    7. 62744
    Prev
    Next
    INDEX
    Explanations

    Google search, patents, and doodles

    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_34/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
     подготовка
    -0.82
    诺
    -0.81
     thuộc
    -0.75
    甲
    -0.72
    线性
    -0.71
    ESSION
    -0.71
    óra
    -0.70
     Cram
    -0.70
    Thu
    -0.69
    öny
    -0.69
    POSITIVE LOGITS
     Google
    1.60
    Google
    1.34
     Doodle
    1.23
     google
    1.10
     GOOGLE
    1.08
     doodle
    1.04
    Doodle
    1.01
    google
    0.98
    GOOGLE
    0.97
     Goo
    0.94
    Activations Density 0.020%

    No Known Activations