© 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. 13262
    Prev
    Next
    INDEX
    Explanations

    news reports and dates

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

    active directory errors

    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
     韓国
    0.54
    سی
    0.52
    .].
    0.52
    점
    0.51
     представлены
    0.51
     作詞
    0.50
     सक
    0.49
     わ
    0.49
     köszön
    0.49
    trashButton
    0.48
    POSITIVE LOGITS
     CRL
    0.46
     serialized
    0.45
    ‒
    0.43
     mandatory
    0.41
     phys
    0.39
     CRM
    0.39
    opt
    0.38
     IL
    0.38
     OPT
    0.38
     séjour
    0.38
    Activations Density 0.000%

    No Known Activations