© 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. 15196
    Prev
    Next
    INDEX
    Explanations

    past events and accomplishments

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

    accomplishments and quantified results

    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
     atau
    0.52
     वैसे
    0.51
     বুঝি
    0.46
     semoga
    0.45
     But
    0.44
    ようです
    0.44
     शायद
    0.44
     davvero
    0.43
     familiar
    0.42
     হয়তো
    0.42
    POSITIVE LOGITS
    当时
    0.66
    當時
    0.64
     ছিলাম
    0.63
     успешно
    0.61
    ினேன்
    0.60
     damals
    0.58
     работал
    0.58
     erfolgreich
    0.55
     successfully
    0.54
     damal
    0.54
    Activations Density 0.655%

    No Known Activations