© 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. 10-GEMMASCOPE-RES-131K
    7. 14167
    Prev
    Next
    INDEX
    Explanations

    contingent, contingency, concomitant

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

    The neuron is triggered by words that begin with “cont” (e.g., contingent, contingency, concomitant).

    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
     gän
    -2.56
    褙
    -2.52
    GillaGilla
    -2.48
    ㍑
    -2.44
    1
    -2.42
     eccellente
    -2.41
    actéristi
    -2.39
     δύο
    -2.34
    как
    -2.27
     baumwolle
    -2.27
    POSITIVE LOGITS
    ↵
    4.19
    ),
    2.83
    ).
    2.75
    </strong>
    2.58
    ]
    2.55
    と呼ばれる
    2.45
    ’,
    2.22
    
    2.09
    é
    2.09
     Also
    2.06
    Activations Density 0.002%

    No Known Activations