© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14512
    Prev
    Next
    INDEX
    Explanations

    then leads to consequence

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

    then followed by consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    ing
    1.17
    0
    1.14
    {
    1.09
    ho
    1.08
    us
    1.07
    he
    1.06
    :
    1.03
    al
    0.98
    ut
    0.96
    um
    0.96
    POSITIVE LOGITS
    ल
    0.94
    на
    0.89
    ก
    0.82
    спубли
    0.75
    наў
    0.73
    나
    0.73
    มาร
    0.70
    크
    0.70
    رفة
    0.69
    서는
    0.69
    Activations Density 0.094%

    No Known Activations