© 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. 329
    Prev
    Next
    INDEX
    Explanations

    there is/are/was

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

    there is/are/was/were

    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
    racting
    0.21
     setzt
    0.19
    :{
    0.18
     durchgeführt
    0.17
     initializing
    0.17
     violates
    0.17
     þat
    0.16
    .}
    0.16
    ized
    0.16
     besitzt
    0.16
    POSITIVE LOGITS
     a
    0.24
     no
    0.23
     is
    0.22
     کوئی
    0.21
     plenty
    0.21
     more
    0.20
     alot
    0.19
     been
    0.19
     beaucoup
    0.18
     mucho
    0.17
    Activations Density 0.813%

    No Known Activations