© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99009
    Prev
    Next
    INDEX
    Explanations

    lists and enumerations

    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
     военных
    -1.05
     any
    -1.04
     or
    -1.00
     producten
    -0.94
     orice
    -0.90
     amado
    -0.88
     roar
    -0.87
     anglaise
    -0.84
     bermanfaat
    -0.83
     cualquier
    -0.83
    POSITIVE LOGITS
     introduction
    1.12
    ちょっと
    0.98
     rudi
    0.97
    introduction
    0.97
     introduces
    0.95
     kinda
    0.95
     более
    0.91
     concludes
    0.91
     artig
    0.91
     introduce
    0.89
    Activations Density 0.026%

    No Known Activations