© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8096
    Prev
    Next
    INDEX
    Explanations

    reform and transform derivations

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

    Transformer architecture

    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
    ی
    0.48
    ייה
    0.46
     बिलियन
    0.42
    有问题
    0.41
    ILLE
    0.39
    얀
    0.39
    ケー
    0.39
    خ
    0.39
    安排
    0.39
    %";
    0.38
    POSITIVE LOGITS
    ulate
    1.11
    atted
    1.11
    ative
    1.02
    ational
    0.98
    ations
    0.91
    ulations
    0.90
    ulation
    0.90
    idable
    0.89
    ulating
    0.86
    ulated
    0.84
    Activations Density 0.024%

    No Known Activations