© 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. 14841
    Prev
    Next
    INDEX
    Explanations

    technical features and names

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

    related to or preceding symbols

    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
    事
    0.36
    琟
    0.36
    werden
    0.35
    antly
    0.34
    Ingrese
    0.34
    制度
    0.34
     lain
    0.33
    슴
    0.33
    격
    0.33
     MSNBC
    0.33
    POSITIVE LOGITS
    とその
    0.50
    及其
    0.45
     correspondingly
    0.39
    !='
    0.39
    鉢
    0.39
    あって
    0.38
     அதன்
    0.38
     соответству
    0.36
     असल
    0.36
     corresponding
    0.36
    Activations Density 0.108%

    No Known Activations