© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11366
    Prev
    Next
    INDEX
    Explanations

    questions and answers

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

    dialogue and questions

    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_40_width_16k_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
    %，
    0.46
    ','
    0.42
    Parameters
    0.42
     ，
    0.42
     حسب
    0.41
    ,\,\,\,\
    0.40
    ;,
    0.39
    ，
    0.38
    Dictionaries
    0.37
    Domestic
    0.37
    POSITIVE LOGITS
     Q
    0.79
    Q
    0.79
     interviewer
    0.78
    Ｑ
    0.71
     narrator
    0.65
    Narr
    0.59
     क्यू
    0.57
     Narr
    0.52
    主持人
    0.51
    𝑄
    0.51
    Activations Density 0.240%

    No Known Activations