© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103235
    Prev
    Next
    INDEX
    Explanations

    give it a go

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

    The neuron consistently fires on instances of the verb “give.”

    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
    辈子
    -0.84
    したが
    -0.83
     ability
    -0.80
     ihres
    -0.77
     आहे
    -0.76
    charest
    -0.76
     عندما
    -0.76
    いっぱ
    -0.75
     sacraments
    -0.74
     포함
    -0.72
    POSITIVE LOGITS
     it
    1.36
     ourselves
    1.02
     each
    0.86
     הע
    0.85
     созда
    0.85
     seri
    0.85
    jekk
    0.85
    ┐
    0.85
     reina
    0.85
     this
    0.84
    Activations Density 0.019%

    No Known Activations