© 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. 90181
    Prev
    Next
    INDEX
    Explanations

    dates preceding construction

    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
    ὺς
    -0.88
     Deja
    -0.85
     planification
    -0.85
    uatu
    -0.84
     Feinde
    -0.83
    髂
    -0.83
    長
    -0.81
    zadas
    -0.79
     ロン
    -0.79
    wki
    -0.79
    POSITIVE LOGITS
     built
    1.48
     circa
    1.42
     constructed
    1.32
     construction
    1.29
     Built
    1.20
    circa
    1.13
    built
    1.12
     build
    1.11
     construido
    1.09
     construite
    1.09
    Activations Density 0.042%

    No Known Activations