© 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. 56573
    Prev
    Next
    INDEX
    Explanations

    states three facts, incorrect bills, life expectancy

    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
    Negative Logits
    采取
    0.45
     эту
    0.44
     Antit
    0.43
     Defensive
    0.42
     Destroy
    0.42
    сную
    0.41
    Что
    0.41
     Reasonable
    0.41
    菪
    0.41
     Bankruptcy
    0.40
    POSITIVE LOGITS
     היו
    0.46
     неред
    0.43
     pasti
    0.42
    ificazione
    0.42
     lascia
    0.41
    geschossiges
    0.40
     regressions
    0.39
    گي
    0.39
    pele
    0.39
    gü
    0.39
    Activations Density 0.019%

    No Known Activations