© 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. 22-GEMMASCOPE-RES-131K
    7. 14740
    Prev
    Next
    INDEX
    Explanations

    Travis Scott

    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
    Not in Any Lists

    No Comments

    Negative Logits
     falleció
    -0.96
     March
    -0.93
    都需要
    -0.87
     prioritized
    -0.87
    IORITY
    -0.86
    ziers
    -0.86
     ويت
    -0.84
    信息的
    -0.82
     سبتمبر
    -0.82
    pense
    -0.81
    POSITIVE LOGITS
     it
    0.98
     amelior
    0.91
     białe
    0.91
     control
    0.91
    Monitoring
    0.90
    monitoring
    0.88
    ividu
    0.88
     positiva
    0.87
     monitoring
    0.87
    ihnachten
    0.87
    Activations Density 0.042%

    No Known Activations