© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32636
    Prev
    Next
    INDEX
    Explanations

    one of

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

    This neuron fires on the word “one” when it’s used in “one of…” ranking or list phrases (e.g. “one of the best,” “one of the most,” etc.).

    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
     ± 
    -1.02
    featuring
    -0.95
     pomys
    -0.92
     WEEKLY
    -0.91
     aguja
    -0.89
    ﻼ
    -0.84
    übers
    -0.84
     pensando
    -0.83
    ţi
    -0.82
     patrulla
    -0.82
    POSITIVE LOGITS
     hell
    2.94
     heck
    2.78
     of
    2.02
     Hell
    1.83
    hell
    1.81
    Hell
    1.71
     Heck
    1.63
    heck
    1.61
    Heck
    1.44
     HELL
    1.41
    Activations Density 0.015%

    No Known Activations