© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56745
    Prev
    Next
    INDEX
    Explanations

    refused, sometimes, normal

    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
    Negative Logits
    േ
    0.45
    毎回
    0.42
    ाम
    0.42
    露出
    0.42
     commentators
    0.42
     timeLeft
    0.42
    ട
    0.41
    ક્
    0.41
     Há
    0.41
    阏
    0.41
    POSITIVE LOGITS
     Rhino
    0.52
    shund
    0.45
    하여
    0.45
    ifier
    0.44
    జీ
    0.44
    﨑
    0.44
     tượng
    0.43
    quant
    0.43
     用于
    0.43
     হইয়৷
    0.43
    Activations Density 0.028%

    No Known Activations