© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116856
    Prev
    Next
    INDEX
    Explanations

    Nobel Prize

    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
    National
    -0.91
     National
    -0.84
     Spezial
    -0.80
    national
    -0.78
     Nacional
    -0.76
     competitive
    -0.74
     ofreci
    -0.73
     perumahan
    -0.73
    intar
    -0.73
     राष्ट
    -0.71
    POSITIVE LOGITS
     Nobel
    1.63
    Nobel
    1.40
     Prize
    1.30
     prize
    1.25
    Prize
    1.16
     Prizes
    1.16
    prize
    1.03
     awarded
    1.03
     prizes
    1.02
    Nob
    1.02
    Activations Density 0.022%

    No Known Activations