© 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
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 414
    Prev
    Next
    INDEX
    Explanations

    't' following a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    ς
    0.49
    s
    0.45
    ات
    0.41
    𝘀
    0.37
    ことになる
    0.36
    শৃঙ্খলা
    0.35
    ের
    0.34
    ों
    0.34
     clots
    0.33
    szer
    0.31
    POSITIVE LOGITS
    {
    0.39
    d
    0.37
    n
    0.37
    ان
    0.36
    有两种
    0.36
    ับ
    0.35
    zelfde
    0.35
    ل
    0.34
    l
    0.34
    ne
    0.33
    Activations Density 0.787%

    No Known Activations