© 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. 200101
    Prev
    Next
    INDEX
    Explanations

    concepts and their follow-ons

    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
    mują
    0.46
    bleshooting
    0.45
     underage
    0.44
    ğinin
    0.44
     alerting
    0.44
    关注
    0.43
    面试
    0.42
     cardiologist
    0.42
    鿉
    0.41
     safeguarding
    0.40
    POSITIVE LOGITS
     hok
    0.49
     creams
    0.48
     aby
    0.46
     danno
    0.45
     ooz
    0.44
     ko
    0.44
     keram
    0.43
     kum
    0.43
    Gloss
    0.43
     Sunlight
    0.42
    Activations Density 0.010%

    No Known Activations