© 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. 31-GEMMASCOPE-2-RES-16K
    7. 130
    Prev
    Next
    INDEX
    Explanations

    when

    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_31_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
    เพราะ
    0.34
     เพราะ
    0.31
    _
    0.31
    จาก
    0.30
     ซึ่ง
    0.30
    ซึ่ง
    0.29
    以及
    0.29
     เพื่อ
    0.29
    เนื่อง
    0.29
    ※
    0.29
    POSITIVE LOGITS
     you
    0.60
     they
    0.58
     we
    0.56
     someone
    0.54
     youre
    0.52
     it
    0.52
     there
    0.48
     вони
    0.46
     они
    0.46
     somebody
    0.46
    Activations Density 0.967%

    No Known Activations