© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10922
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths, especially those ending in pdf or html

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

    links followed by closing bracket

    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
    wire
    0.45
     Fif
    0.41
    ानि
    0.40
    /
    0.38
    /${
    0.37
     planet
    0.37
    authorization
    0.37
    篭
    0.37
    نهار
    0.36
    day
    0.36
    POSITIVE LOGITS
     unge
    0.46
    #.
    0.44
     مؤرشف
    0.41
    ϳ
    0.41
     الهول
    0.39
     kissed
    0.39
     abgerufen
    0.38
     ampio
    0.38
    وسیع
    0.38
    묽
    0.38
    Activations Density 0.018%

    No Known Activations