© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2997
    Prev
    Next
    INDEX
    Explanations

    cats

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

    The neuron spikes on programming‐related resource names—especially JavaScript module or file names (e.g. “validation,” “tooltip,” “registry,” “element,” etc.)—as they appear at the end of URLs.

    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
    i
    0.57
    No
    0.56
    Phase
    0.52
    Test
    0.51
    Sets
    0.50
    Tunnel
    0.50
    Match
    0.48
    Loop
    0.47
     o
    0.47
    Custom
    0.46
    POSITIVE LOGITS
     leftist
    0.61
     vínculo
    0.60
     नवरात्रि
    0.59
     diferite
    0.58
    ურნ
    0.57
     infix
    0.57
     hospice
    0.57
    ကြောင်း
    0.57
     বিষয়ক
    0.57
    ujú
    0.56
    Activations Density 0.000%

    No Known Activations