© 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. 98068
    Prev
    Next
    INDEX
    Explanations

    sign language and deaf communication

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

    The neuron fires on mentions of “Sign Language,” especially in names or descriptions of sign languages.

    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
     listens
    -0.70
    udp
    -0.68
    ຸ
    -0.67
     cev
    -0.66
     面包
    -0.66
     entendre
    -0.66
    ctrons
    -0.65
     หัว
    -0.65
    twitter
    -0.64
     saliv
    -0.64
    POSITIVE LOGITS
     signing
    3.30
     Signing
    2.97
    Signing
    2.81
     sign
    2.63
     signed
    2.55
     Signed
    2.45
     Sign
    2.34
    signing
    2.31
     SIGN
    2.27
     signings
    2.27
    Activations Density 0.024%

    No Known Activations