© 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. 116037
    Prev
    Next
    INDEX
    Explanations

    examines work, adjust, proceed

    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
    wijl
    -0.98
    Setiap
    -0.96
    essional
    -0.93
     inspiri
    -0.92
    urier
    -0.92
     ។
    -0.91
    muje
    -0.86
     tjen
    -0.86
     queijo
    -0.85
    ūra
    -0.84
    POSITIVE LOGITS
    erequisites
    0.91
    iliki
    0.88
    listair
    0.86
     think
    0.83
    IMIN
    0.80
     decisivo
    0.79
     grasp
    0.78
     understood
    0.77
     check
    0.77
     proceed
    0.77
    Activations Density 0.112%

    No Known Activations