© 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. 385
    Prev
    Next
    INDEX
    Explanations

    prefix plus suffix forming words

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

    prefix indicating negation or negativity

    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
     большая
    0.30
    提供
    0.28
    锯
    0.26
    指定
    0.26
     فقط
    0.26
     ONLY
    0.26
     повністю
    0.26
    除了
    0.25
     tanque
    0.25
     BFF
    0.25
    POSITIVE LOGITS
     admon
    0.26
     impover
    0.23
    political
    0.23
     despot
    0.22
     semblable
    0.22
     idolat
    0.22
    {\'
    0.21
     tormented
    0.21
     uprisings
    0.21
    ulatory
    0.21
    Activations Density 0.714%

    No Known Activations