© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22138
    Prev
    Next
    INDEX
    Explanations

    part of things

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

    The neuron fires on occurrences of the word “part” (as in “part of …”), marking section or segment labels in the text.

    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
     that
    -1.95
     what
    -1.53
     for
    -1.51
     into
    -1.48
     this
    -1.34
     through
    -1.32
     ervaren
    -1.28
     like
    -1.25
     according
    -1.25
     across
    -1.24
    POSITIVE LOGITS
    潆
    1.69
    alism
    1.61
     их
    1.53
     usw
    1.53
    苜
    1.49
    ently
    1.48
     teh
    1.48
    uliert
    1.45
    tably
    1.43
     ‚
    1.42
    Activations Density 0.025%

    No Known Activations