© 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. 10-GEMMASCOPE-RES-131K
    7. 118839
    Prev
    Next
    INDEX
    Explanations

    sign of

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

    The neuron is triggered by the word “sign” (in contexts where something is presented as an indicator or symptom).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    祤
    -1.73
    是这样的
    -1.69
    ৢ
    -1.63
    quations
    -1.63
     incarceration
    -1.59
     arkas
    -1.57
    ｬ
    -1.51
    cluse
    -1.50
    trata
    -1.50
     atheist
    -1.47
    POSITIVE LOGITS
     who
    1.92
    re
    1.78
     that
    1.70
     how
    1.63
    man
    1.62
    能够
    1.61
    ka
    1.59
     kafe
    1.58
    焿
    1.57
     diki
    1.56
    Activations Density 0.011%

    No Known Activations