© 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-262K
    7. 4665
    Prev
    Next
    INDEX
    Explanations

    singularity or sameness

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    
    0.39
     알아
    0.38
     lesquels
    0.38
     значений
    0.38
    が含ま
    0.37
     例えば
    0.37
    lerine
    0.37
    :
    0.36
     lesquelles
    0.36
     relaj
    0.36
    POSITIVE LOGITS
    ed
    0.47
    ون
    0.45
    I
    0.42
    ే
    0.37
    Data
    0.36
    ت
    0.36
    ار
    0.35
    experiences
    0.35
    services
    0.35
     Of
    0.34
    Activations Density 0.468%

    No Known Activations