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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16714
    Prev
    Next
    INDEX
    Explanations

    asserting claims, defiance

    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
    broccoli
    0.46
     Broccoli
    0.41
    брав
    0.41
     ஊக்கு
    0.41
    勧
    0.40
    恭
    0.40
    分
    0.39
    矚
    0.38
     goss
    0.38
     بڑھ
    0.38
    POSITIVE LOGITS
     defiant
    0.90
     defiance
    0.89
     주장
    0.75
     disput
    0.73
     claiming
    0.71
     claims
    0.70
     defi
    0.69
     asserts
    0.68
     claimed
    0.68
     দাবি
    0.67
    Activations Density 0.113%

    No Known Activations