© 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. 91003
    Prev
    Next
    INDEX
    Explanations

    meeting celebrities and idols

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

    The neuron fires on words and phrases describing crowd reactions or excitement (e.g., shrieks, excited, chanting, reached out, 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
    태
    -1.02
    volezza
    -0.90
    viewBox
    -0.85
    átiles
    -0.83
     celebrations
    -0.83
    𝗦
    -0.82
     verlassen
    -0.80
    OREM
    -0.79
    Bal
    -0.79
    笑笑
    -0.79
    POSITIVE LOGITS
     fang
    1.73
     autograph
    1.73
     fan
    1.52
     celebrity
    1.43
     meet
    1.22
    fan
    1.21
     idol
    1.20
     fans
    1.20
     handshake
    1.16
     meeting
    1.14
    Activations Density 0.039%

    No Known Activations