Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12427
    Prev
    Next
    INDEX
    Explanations

    much greater degree

    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_31_width_16k_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
    㠻
    0.40
     estaban
    0.39
     If
    0.39
    睉
    0.39
    If
    0.38
     Unless
    0.38
     Krause
    0.38
     entweder
    0.37
    ͑
    0.37
     कोशिश
    0.37
    POSITIVE LOGITS
     훨씬
    0.74
    훨
    0.71
     allora
    0.66
     гораздо
    0.61
     тогда
    0.59
     wtedy
    0.58
     THEN
    0.57
    就可以了
    0.57
     wówczas
    0.55
    then
    0.55
    Activations Density 0.235%

    No Known Activations