© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3726
    Prev
    Next
    INDEX
    Explanations

    Just, First

    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_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     heralded
    0.60
    માં
    0.58
    などに
    0.55
     decency
    0.54
    :
    0.54
     obscene
    0.53
    ແລະ
    0.52
     поведения
    0.52
     Caedwalla
    0.52
     있고
    0.51
    POSITIVE LOGITS
    ير
    0.53
    Runtime
    0.51
    Remote
    0.49
    ൺ
    0.48
    الم
    0.47
    Exception
    0.47
    ILA
    0.46
     neues
    0.46
    Instrumentation
    0.44
     Европей
    0.44
    Activations Density 0.160%

    No Known Activations