© 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. 821
    Prev
    Next
    INDEX
    Explanations

    comparison

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

    comparison

    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
     পরস্পর
    0.39
    淈
    0.39
     उन्हीं
    0.39
    ński
    0.38
     যেন
    0.37
    ശന
    0.37
    ᐱ
    0.36
    ോടെ
    0.35
    ੦
    0.34
     poitrine
    0.34
    POSITIVE LOGITS
     compared
    4.47
    compared
    4.28
    Compared
    3.89
     Compared
    3.84
     dibandingkan
    3.52
     dibanding
    3.33
    相比
    3.27
     مقار
    2.91
     сравнению
    2.89
    比べて
    2.86
    Activations Density 0.519%

    No Known Activations