© 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-262K
    7. 26080
    Prev
    Next
    INDEX
    Explanations

    trying to do

    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
    Negative Logits
    Rh
    0.43
     dishonesty
    0.43
    <0xE6>
    0.41
     dishonest
    0.41
     손
    0.40
     unimaginable
    0.40
     Rh
    0.39
     geist
    0.39
     Suite
    0.38
     intelligence
    0.38
    POSITIVE LOGITS
    所以
    0.46
    鰱
    0.44
    াইতে
    0.41
     所以
    0.40
    所以在
    0.40
     групи
    0.40
     objecting
    0.40
     bý
    0.38
    纷纷
    0.38
    
    0.38
    Activations Density 0.011%

    No Known Activations