© 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. 84826
    Prev
    Next
    INDEX
    Explanations

    explain why

    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
    cre
    0.56
    J
    0.50
    class
    0.47
    b
    0.47
    B
    0.47
    on
    0.47
    is
    0.45
    blind
    0.45
    Another
    0.44
    next
    0.43
    POSITIVE LOGITS
     rusak
    0.59
    䀦
    0.58
    㽛
    0.54
     промышлен
    0.54
    婜
    0.53
     арга
    0.51
    刀
    0.51
    㤈
    0.50
    䇢
    0.49
     iccad
    0.49
    Activations Density 0.008%

    No Known Activations