© 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. 13731
    Prev
    Next
    INDEX
    Explanations

    events begin and are found

    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
    Not in Any Lists

    No Comments

    Negative Logits
     этого
    0.52
     PERSON
    0.50
    หรือ
    0.49
    这些人
    0.47
     (
    0.47
     acest
    0.47
     этом
    0.47
     цьому
    0.47
    或
    0.46
     इस
    0.46
    POSITIVE LOGITS
     thankfully
    0.63
     fateful
    0.62
     terrifying
    0.61
     luckily
    0.61
     heartbreaking
    0.55
    했지만
    0.55
     shocking
    0.54
     fortunately
    0.54
    Thankfully
    0.54
     unthinkable
    0.52
    Activations Density 0.030%

    No Known Activations