© 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. 34-GEMMASCOPE-RES-131K
    7. 49583
    Prev
    Next
    INDEX
    Explanations

    construction and related actions

    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
    也被
    -0.75
     Statue
    -0.74
    ویی
    -0.74
    endamento
    -0.72
     スリム
    -0.72
    onien
    -0.71
    ਤੀ
    -0.71
     démocratie
    -0.71
    ubei
    -0.71
    竊
    -0.70
    POSITIVE LOGITS
     construction
    4.22
    construction
    3.58
     constructed
    3.42
    Construction
    3.39
     constructing
    3.20
     construct
    3.17
     constructions
    3.16
     Construction
    3.11
     construcción
    3.02
     CONSTRUCTION
    2.98
    Activations Density 0.098%

    No Known Activations