© 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. 1489
    Prev
    Next
    INDEX
    Explanations

    import/link paths

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

    This neuron detects URL strings in HTML link or resource attributes (e.g. the href/src values).

    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
    vZ
    0.54
    eg
    0.52
    hWnd
    0.52
    LE
    0.49
    du
    0.49
    f
    0.48
    h
    0.48
    vb
    0.47
    Bau
    0.47
    sulfanyl
    0.46
    POSITIVE LOGITS
     "./
    0.78
     './
    0.77
     '../../
    0.74
     '../
    0.73
     "../
    0.73
     "../../
    0.73
    ('./
    0.72
    ("./
    0.70
     ../
    0.67
    ('../../
    0.63
    Activations Density 0.001%

    No Known Activations