© 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. 49851
    Prev
    Next
    INDEX
    Explanations

    words ending in er or or

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

    The neuron fires on English words ending in “-er” (agent-noun or doer forms).

    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
     besitzt
    -1.13
    s
    -1.09
    とき
    -1.07
    w
    -1.05
    b
    -0.99
     frig
    -0.97
    讀書
    -0.96
    e
    -0.96
     administrativos
    -0.94
     revolve
    -0.94
    POSITIVE LOGITS
     extraordinaire
    1.80
     who
    1.69
     extraordin
    1.18
     rakyat
    1.04
     død
    1.01
    ially
    1.01
    ING
    1.00
    babu
    1.00
    íng
    0.99
    СЯ
    0.99
    Activations Density 0.158%

    No Known Activations