© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41454
    Prev
    Next
    INDEX
    Explanations

    organized events and gatherings

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

    The neuron is especially sensitive to tokens in headlines or lead‐in sentences that report organized events—e.g. conferences, sessions, inaugurations, or other formally “conducted” gatherings.

    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
     komplet
    -1.38
     preocupaciones
    -1.33
    իմ
    -1.33
    jednoc
    -1.31
    lograph
    -1.31
     publicités
    -1.29
     ligera
    -1.27
    අ
    -1.24
    chsel
    -1.24
     ͜
    -1.23
    POSITIVE LOGITS
     of
    1.84
     at
    1.81
     for
    1.41
     '
    1.30
     series
    1.24
    ому
    1.20
     ‘
    1.20
     by
    1.13
     each
    1.11
     one
    1.10
    Activations Density 0.048%

    No Known Activations