© 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. 10-GEMMASCOPE-RES-131K
    7. 130971
    Prev
    Next
    INDEX
    Explanations

    With followed by noun/phrase

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

    This neuron activates on the word “With,” especially when it begins a clause or sentence.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    on
    -2.17
    你会
    -1.80
    我们会
    -1.69
    us
    -1.65
    in
    -1.65
    k
    -1.63
     will
    -1.62
    }
    -1.58
    l
    -1.58
     our
    -1.51
    POSITIVE LOGITS
    ༴
    1.73
    ઁ
    1.55
    ishment
    1.52
    ｻ
    1.52
    aways
    1.50
    siert
    1.44
     neceſſ
    1.44
     ouvert
    1.44
     quien
    1.43
     akik
    1.41
    Activations Density 0.025%

    No Known Activations