© 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. 119
    Prev
    Next
    INDEX
    Explanations

    hex and tile war game

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

    Graphical User Interface and abdominal and thyroid

    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
    oretically
    0.22
    :
    0.22
     Sekunden
    0.20
     >=
    0.20
    一个
    0.19
     >
    0.19
    x
    0.19
    Size
    0.19
     !=
    0.19
     diamètre
    0.19
    POSITIVE LOGITS
     headquartered
    0.21
     nationwide
    0.19
     dunia
    0.19
     Republike
    0.19
     policym
    0.19
    збеки
    0.18
     метою
    0.18
    едера
    0.18
    ОР
    0.18
    ಯೋಗ
    0.18
    Activations Density 9.980%

    No Known Activations