© 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. 3365
    Prev
    Next
    INDEX
    Explanations

    android maps google

    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
    uleb
    -0.76
    독
    -0.75
     myeloid
    -0.75
    voyance
    -0.73
    ਲ
    -0.73
    ->{
    -0.73
     tiras
    -0.72
    到着
    -0.71
     }^{\
    -0.71
    lhes
    -0.70
    POSITIVE LOGITS
     Google
    0.89
    GOOGLE
    0.82
    ames
    0.81
     exploited
    0.79
     fragment
    0.78
    zzi
    0.76
    fragment
    0.76
     google
    0.76
     ad
    0.75
    Corpus
    0.75
    Activations Density 0.003%

    No Known Activations