© 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. 43144
    Prev
    Next
    INDEX
    Explanations

    actions followed by prepositions

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

    The neuron strongly activates on past‐participle (often passive‐voice) verb forms ending in “-ed” (e.g. conducted, rendered, given, committed, launched).

    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
     Examin
    -1.52
     yaris
    -1.46
     valentino
    -1.45
     they
    -1.44
     ferrari
    -1.42
     maske
    -1.42
     ortop
    -1.41
     vespa
    -1.39
     credi
    -1.38
     renault
    -1.37
    POSITIVE LOGITS
     in
    2.27
     a
    1.45
     Prozess
    1.35
     zprávy
    1.33
     promoção
    1.28
     quedaron
    1.27
     mlad
    1.26
     M
    1.24
     nejlepší
    1.23
    躂
    1.22
    Activations Density 0.260%

    No Known Activations