© 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. 55841
    Prev
    Next
    INDEX
    Explanations

    kapacitor

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

    The neuron strongly activates on any token fragment containing the character sequence “cap” (in any casing), as found in place or personal names like “Caprarola,” “Capone,” “Kapurthala,” etc.

    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
    лимпий
    -0.81
    แฟน
    -0.75
    aurait
    -0.75
    mcg
    -0.74
    istry
    -0.72
     patient
    -0.71
    czer
    -0.68
     each
    -0.68
    えば
    -0.67
    ICZ
    -0.67
    POSITIVE LOGITS
    벵
    0.76
    יל
    0.71
     COME
    0.71
    provide
    0.71
     desertcart
    0.70
     Hock
    0.69
    定義
    0.69
    ⋒
    0.68
     بف
    0.68
     cap
    0.67
    Activations Density 0.031%

    No Known Activations