© 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. 6862
    Prev
    Next
    INDEX
    Explanations

    technical text snippets

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

    programming constructs

    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
    ჯგუფი
    0.57
     ಚುನಾವಣ
    0.47
    ”、
    0.47
     मातरम
    0.46
     使い
    0.46
    ㄼ
    0.45
     বিটিআই
    0.44
    ）・
    0.44
    ുപത്രി
    0.44
     ಅಂಶ
    0.44
    POSITIVE LOGITS
    er
    0.66
    <blockquote>
    0.66
    o
    0.65
    ar
    0.60
    i
    0.60
    a
    0.59
    /*
    0.58
    ing
    0.57
    ↵↵
    0.57
    us
    0.55
    Activations Density 0.017%

    No Known Activations