© 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. 6924
    Prev
    Next
    INDEX
    Explanations

    inferring and concluding

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

    The neuron is primarily sensitive to the character sequence “infer” (e.g. in words like “inferring”).

    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
     &=&
    -0.76
    tigkeit
    -0.75
    brio
    -0.72
     البط
    -0.70
     Vista
    -0.70
     Juvenile
    -0.69
     adolescent
    -0.68
     Stade
    -0.68
     Fork
    -0.68
     NFT
    -0.68
    POSITIVE LOGITS
     infer
    5.06
     inference
    5.03
     inferences
    4.78
     inferred
    4.63
    infer
    4.50
     Inference
    4.25
     Infer
    4.09
    inference
    3.98
    Inference
    3.83
    Infer
    3.75
    Activations Density 0.105%

    No Known Activations