© 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. 14619
    Prev
    Next
    INDEX
    Explanations

    books and authors

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

    full bloom of awareness

    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
     hubby
    0.69
     tentunya
    0.60
     malheureusement
    0.53
    ＆
    0.53
     effettuare
    0.52
     العديد
    0.51
     =>{
    0.51
    抨
    0.51
     sizlerle
    0.50
     दिसून
    0.49
    POSITIVE LOGITS
     fucked
    0.59
     fucking
    0.58
     Matisse
    0.56
     luminous
    0.55
     etcétera
    0.53
     étrang
    0.52
     Kafka
    0.51
    Kafka
    0.50
     Wittgenstein
    0.50
     shit
    0.49
    Activations Density 0.362%

    No Known Activations