© 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-65K
    7. 16971
    Prev
    Next
    INDEX
    Explanations

    how things relate

    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_65k_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
     কীভাবে
    0.41
    习
    0.40
     تقديم
    0.40
     أمر
    0.40
     எப்படி
    0.40
     [<
    0.39
     Umgang
    0.38
     سلو
    0.38
     ஒன்றை
    0.38
    <
    0.38
    POSITIVE LOGITS
     excelled
    0.48
     improved
    0.48
     differed
    0.45
     benefitted
    0.45
     benefitting
    0.45
     উপকৃত
    0.45
     മിക
    0.45
     ticked
    0.44
     aide
    0.44
     improves
    0.43
    Activations Density 0.157%

    No Known Activations