© 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. 67412
    Prev
    Next
    INDEX
    Explanations

    booby trapped

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

    The neuron strongly activates on words containing the “bog/boog/bug” letter sequence (e.g. boogeyman, boogie, bogie, bogey, buggies, hobgoblins, bogus, booby-trapped).

    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
    “
    -2.66
    氿
    -2.20
    
    -2.17
    想了
    -2.06
     we
    -2.00
     ANY
    -1.98
    見る
    -1.98
    unicaciones
    -1.97
     RSITY
    -1.91
    に於
    -1.91
    POSITIVE LOGITS
    y
    1.94
    那我
    1.90
    ೧
    1.89
    Tetapi
    1.86
     große
    1.84
    ями
    1.83
    etlen
    1.82
    ाउनलोड
    1.80
    然后
    1.80
    iconductors
    1.80
    Activations Density 0.003%

    No Known Activations