© 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. 22-GEMMASCOPE-RES-131K
    7. 128998
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on terms and phrases relating to video‐based conferencing and remote meeting technology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    online communication and messaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     of
    -1.23
    }^{\
    -1.21
    ,:)
    -1.19
     betweenstory
    -1.06
     changeable
    -1.05
    ^{\
    -1.02
    dech
    -1.02
    mäßige
    -1.01
     државе
    -1.00
    lrrr
    -1.00
    POSITIVE LOGITS
     communication
    1.41
    Used
    1.35
    RTSN
    1.27
     ledit
    1.23
    alties
    1.23
     tarvit
    1.20
    capabilities
    1.20
     capabilities
    1.16
    对面
    1.15
     nhau
    1.13
    Activations Density 0.043%

    No Known Activations