© 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. 76011
    Prev
    Next
    INDEX
    Explanations

    written in

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

    The neuron fires strongly on regular past-participle verbs (–ed forms) used as descriptors (e.g., dressed, measured, rated).

    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
     installé
    -1.38
     cálido
    -1.33
     cómodo
    -1.33
     emisiones
    -1.30
     diámetro
    -1.30
     zaradi
    -1.29
     océano
    -1.28
     acogedor
    -1.27
    dentro
    -1.25
     energías
    -1.25
    POSITIVE LOGITS
     in
    6.94
     σε
    1.90
     în
    1.75
     In
    1.60
     در
    1.51
     dalam
    1.39
     في
    1.30
    in
    1.30
     в
    1.28
    ใน
    1.27
    Activations Density 0.203%

    No Known Activations