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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 6840
    Prev
    Next
    INDEX
    Explanations

    adding or including content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     have
    0.88
    0
    0.88
     you
    0.85
     HAVE
    0.81
    {//
    0.81
    কে
    0.79
    이랑
    0.77
    ৯
    0.77
    4
    0.75
     إذا
    0.74
    POSITIVE LOGITS
    ل
    1.41
    l
    1.39
    i
    1.33
    in
    1.23
    ul
    1.17
    ล
    1.13
    л
    1.09
    as
    1.05
    ו
    1.05
    n
    1.02
    Activations Density 0.092%

    No Known Activations