© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7645
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on isolated non‐ASCII codepoint tokens (e.g. mis-decoded byte sequences or embedded numeric/Unicode artifacts), i.e. garbled or unexpected character encodings.

    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
     =
    0.93
     {
    0.73
     /*
    0.71
     null
    0.70
     ()
    0.70
     ==
    0.68
     //
    0.68
    ())
    0.67
     Kullan
    0.67
     allowNull
    0.66
    POSITIVE LOGITS
    ेंद्रीय
    0.91
     निजामाच्या
    0.88
     अल्को
    0.84
     आरमार
    0.81
     आरमारा
    0.80
     सूत्रकृ
    0.80
     इंग्लंड
    0.80
    प्टेंबर
    0.79
    नावश्यक
    0.79
     घटस्फोट
    0.79
    Activations Density 0.000%

    No Known Activations