© 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. 9676
    Prev
    Next
    INDEX
    Explanations

    disclaimermodelexplicitcontentrapediscriminationstorylanguagesignincapable

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

    The neuron primarily detects backslash characters (“\”) in the text.

    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
     zile
    0.71
    ेन
    0.70
    t
    0.68
     நன்ற
    0.67
    tests
    0.65
     vej
    0.65
     Viz
    0.64
     ਦ
    0.62
    Გ
    0.62
    ジャケット
    0.61
    POSITIVE LOGITS
    gesi
    0.86
    шают
    0.83
     Adapun
    0.82
    गें
    0.81
     diatomic
    0.80
    물
    0.79
    ually
    0.78
    itteln
    0.77
    囊
    0.77
    стые
    0.77
    Activations Density 0.000%

    No Known Activations