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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3849
    Prev
    Next
    INDEX
    Explanations

    sentence endings and related concepts

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

    end of descriptive phrases

    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
    旖
    0.33
    フラ
    0.33
    裵
    0.32
     foul
    0.32
     periódico
    0.31
    返回值
    0.30
    മീ
    0.30
     reeks
    0.30
    वार
    0.29
    ưởng
    0.29
    POSITIVE LOGITS
    .".
    0.77
     […]
    0.66
    .”.
    0.66
     nbsp
    0.64
     ."
    0.64
    !".
    0.63
    ,"
    0.62
    ."-
    0.62
     theyre
    0.62
     例文帳に追加
    0.61
    Activations Density 1.798%

    No Known Activations