© 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. 108119
    Prev
    Next
    INDEX
    Explanations

    SQL queries and definitions

    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
     famed
    -0.75
    dbo
    -0.75
     investigated
    -0.72
     rare
    -0.71
     znacz
    -0.70
     famosa
    -0.69
     activated
    -0.66
    캘
    -0.65
     durable
    -0.65
     controlled
    -0.65
    POSITIVE LOGITS
    ROUTINE
    0.85
     ROUT
    0.85
     Тай
    0.83
    Symb
    0.82
     שוליים
    0.82
     Vall
    0.80
    ⍝
    0.80
    כשיו
    0.79
    boru
    0.79
     σχ
    0.79
    Activations Density 0.024%

    No Known Activations