© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9533
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by text about wood‐borer/termite infestation and professional fumigation or pest‐control services.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    čené
    0.84
    âge
    0.74
    archiw
    0.71
    ğın
    0.71
    рк
    0.70
    ꯠ
    0.70
    ťou
    0.69
    ਾਲ
    0.68
    ający
    0.68
    kušen
    0.68
    POSITIVE LOGITS
    er
    0.86
    s
    0.80
     aporta
    0.80
     CTA
    0.79
     ZH
    0.79
     ecosystem
    0.79
     sensitively
    0.79
     a
    0.77
     PLHIV
    0.77
     segue
    0.77
    Activations Density 17.418%

    No Known Activations