© 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. 43483
    Prev
    Next
    INDEX
    Explanations

    parcels and shipping

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

    The neuron strongly activates on occurrences of the word “parcel” (and its plural) in a shipping/delivery context.

    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
    Ⴀ
    -2.34
    AutoresizingMask
    -2.33
     pokoje
    -2.33
    旰
    -2.28
    ୃ
    -2.22
    
    -2.19
    ти
    -2.17
     完了
    -2.16
     klubben
    -2.09
     questionSearch
    -2.08
    POSITIVE LOGITS
    u
    2.97
    er
    2.75
    S
    2.67
    —
    2.50
     
    2.38
    to
    2.25
    uſe
    2.23
     …
    2.23
     untuk
    2.14
     стал
    2.13
    Activations Density 0.007%

    No Known Activations