© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13708
    Prev
    Next
    INDEX
    Explanations

    accessing online content

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

    URLs containing common path segments

    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_31_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
    artikel
    0.48
     Abgerufen
    0.47
     مؤرشف
    0.46
    april
    0.45
    और
    0.45
    alka
    0.44
     Understanding
    0.44
    .=
    0.43
    wrote
    0.43
     понрави
    0.43
    POSITIVE LOGITS
     olması
    0.47
    /${
    0.40
     condições
    0.39
     tú
    0.39
     dashboards
    0.39
    நி
    0.38
     api
    0.38
    ্রেট
    0.38
     systems
    0.38
    系统
    0.37
    Activations Density 0.026%

    No Known Activations