© 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. 262
    Prev
    Next
    INDEX
    Explanations

    or delimiter

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

    simple to more

    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
     など
    0.21
     不能
    0.19
     沒有
    0.18
     {
    0.18
     nejen
    0.18
     odnosno
    0.18
     എന്നീ
    0.18
     これらの
    0.17
    _
    0.17
     所以
    0.17
    POSITIVE LOGITS
     просто
    0.26
     наоборот
    0.23
     gewoon
    0.20
     simply
    0.20
     downright
    0.20
    поте
    0.19
     outright
    0.19
     conversely
    0.19
    simply
    0.19
    一方で
    0.19
    Activations Density 1.714%

    No Known Activations