© 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. 2960
    Prev
    Next
    INDEX
    Explanations

    omni, ubiqui, all

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

    The neuron detects words that express totality or universality (e.g. omni-, ubiq-, all-).

    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
    zinger
    -0.73
     zost
    -0.73
    heritance
    -0.71
     rendement
    -0.71
    intensity
    -0.69
    clor
    -0.69
     иллюстрация
    -0.67
    sean
    -0.67
     spiegel
    -0.67
    ądze
    -0.66
    POSITIVE LOGITS
     omni
    3.09
     omnis
    2.97
     omnipotent
    2.75
    omni
    2.70
    Omni
    2.47
     Omni
    2.36
     ubiquitous
    2.03
     ubi
    1.96
     almighty
    1.91
    ubi
    1.76
    Activations Density 0.044%

    No Known Activations