© 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. 73485
    Prev
    Next
    INDEX
    Explanations

    cockroach Authors

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

    words related to insects, particularly cockroaches, bed bugs, and roaches.

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

    The neuron activates on occurrences of “roach” (as in “cockroach” or standalone “roach”) in the text.

    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
    "
    -2.77
    o
    -2.14
    that
    -2.14
    LLocation
    -1.96
    #
    -1.90
    )
    -1.84
    ного
    -1.83
    ),
    -1.83
    u
    -1.82
     metav
    -1.73
    POSITIVE LOGITS
    厯
    1.80
    sudadera
    1.77
    Seguridad
    1.75
    逯
    1.70
    毉
    1.70
    tatuajes
    1.69
    ',
    1.63
     sposob
    1.63
    kram
    1.61
    𝖢
    1.61
    Activations Density 0.008%

    No Known Activations