© 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. 7073
    Prev
    Next
    INDEX
    Explanations

    case studies

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

    case where/when/of/task

    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
    ਜ਼
    0.42
    ੋ
    0.41
     количеством
    0.41
    ところ
    0.40
    credible
    0.39
    นน
    0.39
    ைப்
    0.39
     কেমন
    0.38
     quaint
    0.38
    ਰ
    0.38
    POSITIVE LOGITS
     éché
    0.81
     study
    0.77
    Study
    0.77
     STUDY
    0.76
     स्टडी
    0.75
     Study
    0.74
    study
    0.74
     scenario
    0.71
     studies
    0.66
    uality
    0.64
    Activations Density 0.056%

    No Known Activations