© 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. 83673
    Prev
    Next
    INDEX
    Explanations

    how about

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

    The neuron specifically fires on occurrences of the word “how,” especially when it begins a question.

    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
     zależności
    -0.89
    筧
    -0.83
    gros
    -0.78
    停車
    -0.78
     głównie
    -0.77
    礎
    -0.77
    uroy
    -0.76
    pAd
    -0.76
     questions
    -0.75
     plásticos
    -0.74
    POSITIVE LOGITS
     about
    3.27
    About
    1.74
    about
    1.66
    ABOUT
    1.34
     About
    1.23
    bout
    1.13
     ABOUT
    1.12
     dacht
    1.10
     yaklaşık
    1.07
    Would
    1.02
    Activations Density 0.019%

    No Known Activations