© 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. 10-GEMMASCOPE-RES-131K
    7. 43272
    Prev
    Next
    INDEX
    Explanations

    cardboard packaging and materials

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is detect mentions of cardboard or paperboard materials (e.g., “corrugated,” “cardboard,” “board,” “flutes,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     begu
    -1.27
    fang
    -1.25
    AR
    -1.23
     Voyages
    -1.22
    皞
    -1.22
    OG
    -1.21
    OS
    -1.18
    
    -1.18
    AC
    -1.18
    AT
    -1.18
    POSITIVE LOGITS
     start
    1.30
     terlaris
    1.20
     cereal
    1.19
     Remember
    1.17
     Künstler
    1.16
    sejarah
    1.15
     Perhaps
    1.14
    Although
    1.14
    Shortly
    1.14
     our
    1.13
    Activations Density 0.078%

    No Known Activations