© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13056
    Prev
    Next
    INDEX
    Explanations

    bug and debug

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

    The neuron is keyed to any word fragments beginning with “bug,” i.e. tokens containing the substring “bug.”

    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_31_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
    ፈላ
    0.61
     जोरदार
    0.60
     ppb
    0.60
    を出
    0.59
    輝
    0.56
    प
    0.55
    強力
    0.55
    PADDING
    0.54
     изо
    0.54
     tegas
    0.54
    POSITIVE LOGITS
     bug
    0.94
     Bug
    0.88
    Bug
    0.81
     bugs
    0.76
     infestation
    0.75
    bug
    0.74
     BUG
    0.72
    🐜
    0.72
    🐛
    0.70
     Bugs
    0.70
    Activations Density 0.122%

    No Known Activations