© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2112
    Prev
    Next
    INDEX
    Explanations

    wrapping materials

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

    The neuron strongly activates on tokens that occur in recipe‐style imperative steps (e.g. cooking directions).

    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
     Kits
    -0.75
     телефо
    -0.73
    valueOf
    -0.69
     Kazim
    -0.69
    cipline
    -0.69
    ukasz
    -0.69
     Vale
    -0.68
     Sou
    -0.67
    easing
    -0.67
    vore
    -0.67
    POSITIVE LOGITS
     cling
    2.44
     wrapping
    2.41
     bubble
    2.33
     wrap
    2.31
     saran
    2.22
     foil
    2.19
     shrink
    2.08
     Wrap
    2.02
     Saran
    1.98
     cello
    1.95
    Activations Density 0.040%

    No Known Activations