© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1203
    Prev
    Next
    INDEX
    Explanations

    want/or constructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     some
    0.43
     one
    0.42
     a
    0.42
    some
    0.41
     something
    0.40
     nothing
    0.40
     seating
    0.40
     texting
    0.40
    quit
    0.39
    something
    0.39
    POSITIVE LOGITS
     gebruiken
    0.46
     хочет
    0.44
    ឬ
    0.44
     కలిగి
    0.43
     혹은
    0.43
    又は
    0.42
     अथवा
    0.41
     లేదా
    0.41
     أحمد
    0.41
     用于
    0.41
    Activations Density 0.693%

    No Known Activations