© 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. 59013
    Prev
    Next
    INDEX
    Explanations

    past verbs and prepositions

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

    The neuron fires on verbs that express assigning or supplying a value (e.g. “granted,” “null” assignment, “feed”).

    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
     нему
    -1.02
     людьми
    -1.01
     großem
    -0.98
     вами
    -0.98
     προς
    -0.88
     ähnlichen
    -0.88
     neuem
    -0.85
    greifen
    -0.84
     gutem
    -0.83
     ним
    -0.82
    POSITIVE LOGITS
     dem
    2.47
     to
    1.34
     einem
    1.28
    dem
    1.18
    Dem
    1.15
     them
    1.12
     der
    1.07
    แก่
    1.03
     den
    1.00
     DEM
    0.99
    Activations Density 0.024%

    No Known Activations