© 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. 65832
    Prev
    Next
    INDEX
    Explanations

    programming constructs or metadata

    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
    -0.83
     Coleoptera
    -0.81
    cils
    -0.79
    -0.79
     становника
    -0.78
    เภ
    -0.78
    chränkungen
    -0.76
     referrals
    -0.75
    lıyor
    -0.75
    هرة
    -0.75
    POSITIVE LOGITS
    不想
    0.87
    Numero
    0.84
     Surya
    0.83
    rch
    0.78
     Arrays
    0.78
     muitos
    0.77
    ICMP
    0.76
     TypeScript
    0.76
     wielu
    0.75
    ifte
    0.75
    Activations Density 0.000%

    No Known Activations