© 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. 53-GEMMASCOPE-2-RES-65K
    7. 5538
    Prev
    Next
    INDEX
    Explanations

    numbers followed by parenthesis

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

    animals and Chinese

    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_53_width_65k_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
    心中的
    0.42
    gings
    0.39
    nonsense
    0.39
    pleClass
    0.38
    朔
    0.38
     accedere
    0.38
    দ্‌
    0.37
    djang
    0.37
    writeFile
    0.36
    fted
    0.36
    POSITIVE LOGITS
     "".
    0.45
     "
    0.43
     "":
    0.43
     ("
    0.42
     "'";
    0.42
    לק
    0.42
    继续
    0.40
     হল
    0.39
     Ksi
    0.39
     PSI
    0.39
    Activations Density 0.010%

    No Known Activations