© 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. 65896
    Prev
    Next
    INDEX
    Explanations

    screen printing

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

    The neuron activates on numeric values and related tokens found in product specification or pricing fields (e.g. charges, dimensions, imprint areas) in catalog‐style listings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    monial
    -0.83
    wyczaj
    -0.75
    showConfirm
    -0.70
     콘텐츠
    -0.69
    镓
    -0.67
     Zah
    -0.65
    Zah
    -0.65
    }}=\
    -0.65
     demolish
    -0.65
     bibliography
    -0.65
    POSITIVE LOGITS
     screen
    4.22
    screen
    3.42
     Screen
    3.36
     silks
    3.09
    Screen
    3.09
     silk
    2.83
     SCREEN
    2.64
    creen
    2.64
    SCREEN
    2.53
     screened
    2.41
    Activations Density 0.082%

    No Known Activations