© 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. 63113
    Prev
    Next
    INDEX
    Explanations

    oblig and olig sequences

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

    scientific prefixes like "oblig-", "olig-" commonly found in biochemical and biological terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron strongly activates on words containing the character sequence “olig” (as in obligate, oligomer, oligosaccharide, oligodendrocyte, 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
    trico
    -0.91
    Flavor
    -0.83
    ियम
    -0.80
    RelativeLayout
    -0.79
     Flavor
    -0.77
    ijn
    -0.76
    Стан
    -0.75
     Tú
    -0.74
     Dort
    -0.71
    ій
    -0.71
    POSITIVE LOGITS
     oblig
    1.22
    Oblig
    1.08
     Oblig
    1.06
     obligatory
    0.97
     obliged
    0.94
     obrig
    0.92
     obli
    0.87
     OBL
    0.83
    oblig
    0.82
     obligated
    0.81
    Activations Density 0.021%

    No Known Activations