© 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. 22-GEMMASCOPE-RES-131K
    7. 16486
    Prev
    Next
    INDEX
    Explanations

    serialization and loading data

    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
    Negative Logits
     grupo
    -1.02
     effray
    -1.00
    Buhari
    -0.97
     heureuse
    -0.92
    класс
    -0.91
     brasileira
    -0.91
     карте
    -0.90
     tohto
    -0.90
     obrazy
    -0.90
    фотография
    -0.90
    POSITIVE LOGITS
     from
    0.94
     empfangen
    0.85
     it
    0.83
     rispond
    0.81
     monoc
    0.81
    During
    0.81
     has
    0.80
    既存
    0.80
     received
    0.79
    While
    0.79
    Activations Density 0.010%

    No Known Activations