© 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. 31-GEMMASCOPE-2-RES-262K
    7. 9689
    Prev
    Next
    INDEX
    Explanations

    list item descriptors

    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_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
    ،
    0.54
     sported
    0.44
     totiž
    0.39
     หรือ
    0.37
    ，
    0.37
     façons
    0.36
    、
    0.36
    、『
    0.35
     murine
    0.35
    ﭜ
    0.35
    POSITIVE LOGITS
    n
    0.57
    it
    0.54
    do
    0.45
    これは
    0.43
     it
    0.42
    s
    0.42
    no
    0.41
    dw
    0.41
    אי
    0.40
     поэтому
    0.40
    Activations Density 0.219%

    No Known Activations