© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4268
    Prev
    Next
    INDEX
    Explanations

    time units

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

    code syntax and assignments

    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
     作詞
    0.40
    美好的
    0.39
    BtnFill
    0.39
    糇
    0.39
     ಈಗಾಗಲೇ
    0.39
     букмекердик
    0.38
     പിന്നീ
    0.37
    বরের
    0.37
     सार्वजनिक
    0.37
    MathMarks
    0.37
    POSITIVE LOGITS
    ֔
    0.55
    ֑
    0.46
    {}'.
    0.41
    ል።
    0.37
     {}'.
    0.37
     theirs
    0.36
     دیا۔
    0.36
    tos
    0.35
    fid
    0.35
    %@",
    0.34
    Activations Density 0.225%

    No Known Activations