© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98390
    Prev
    Next
    INDEX
    Explanations

    IRB research approval

    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
     IMF
    -0.82
     μην
    -0.79
    ologische
    -0.79
     ảo
    -0.77
     AIC
    -0.77
     thạch
    -0.76
     Ett
    -0.75
     LLP
    -0.75
     hesitating
    -0.74
    плика
    -0.73
    POSITIVE LOGITS
     IRB
    1.17
    IRB
    1.07
     Investigator
    1.06
     investigator
    0.97
    Investigators
    0.96
     investigators
    0.94
     Investigators
    0.92
     research
    0.91
     INSTITUTION
    0.87
     Institutional
    0.82
    Activations Density 0.044%

    No Known Activations