© 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. 84347
    Prev
    Next
    INDEX
    Explanations

    cutting inserts or carbide

    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
    andola
    -0.88
     pleadings
    -0.78
     leather
    -0.76
    ━━━
    -0.75
     Sasuke
    -0.75
    ánicos
    -0.69
    ══
    -0.69
    κιν
    -0.66
    \(
    -0.66
     gos
    -0.66
    POSITIVE LOGITS
     inserts
    1.43
     Inserts
    1.19
     cutting
    1.16
     insert
    1.13
    inser
    1.12
     cutters
    1.05
    insert
    1.04
     inserted
    1.03
    cutting
    1.01
     cutter
    1.00
    Activations Density 0.028%

    No Known Activations