© 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. 118105
    Prev
    Next
    INDEX
    Explanations

    official provincial funeral

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

    The neuron activates on standalone numeric tokens—particularly numbers representing counts, measures, or other quantitative data.

    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
     Ľ
    -0.94
     meus
    -0.93
    ְּ
    -0.86
    ִּ
    -0.85
     capas
    -0.85
     atitude
    -0.84
     Trabal
    -0.82
    sprites
    -0.81
     coment
    -0.81
     GREAT
    -0.79
    POSITIVE LOGITS
     goofy
    0.98
    俺は
    0.91
     スクエア
    0.90
     thus
    0.90
     continually
    0.89
    ほとん
    0.88
     decidedly
    0.88
     tailed
    0.87
     devast
    0.84
    錆
    0.84
    Activations Density 0.001%

    No Known Activations