© 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. 100525
    Prev
    Next
    INDEX
    Explanations

    competitiveness and competitor

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the root “competit” (e.g. competitive, competitiveness).

    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
     prioriti
    -2.22
    ].
    -2.22
    }.
    -2.14
     that
    -2.14
    ).
    -2.05
    }
    -2.02
     extensively
    -1.97
    .).
    -1.95
    יה
    -1.94
    あるので
    -1.90
    POSITIVE LOGITS
    0
    2.55
    geſ
    2.27
    なりません
    2.13
    de
    2.08
     フロア
    1.99
    k
    1.99
    E
    1.97
    臜
    1.96
     fuss
    1.96
    M
    1.91
    Activations Density 0.005%

    No Known Activations