© 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. 34-GEMMASCOPE-RES-131K
    7. 57134
    Prev
    Next
    INDEX
    Explanations

    Human-Computer Interaction (HCI)

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

    The neuron is strongly activated by capitalized proper nouns and named entities (e.g., people’s names, organization and institution names, and other title-like tokens).

    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
    wasm
    -0.81
     KV
    -0.81
     mins
    -0.80
     chemical
    -0.77
    太子
    -0.75
     addObject
    -0.74
    entrum
    -0.72
    lidae
    -0.72
    aticano
    -0.71
     mathematical
    -0.70
    POSITIVE LOGITS
     HCI
    1.48
    HCI
    1.46
     usability
    1.36
     CHI
    1.36
    CHI
    1.28
    hci
    1.25
    Design
    1.20
    デザイン
    1.17
     Usability
    1.16
     Design
    1.15
    Activations Density 0.036%

    No Known Activations