© 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. 40-GEMMASCOPE-2-RES-16K
    7. 7769
    Prev
    Next
    INDEX
    Explanations

    code output

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     simulated
    0.41
     ¶
    0.41
    াদিত
    0.36
    VisualStudio
    0.35
     ʼ
    0.35
     alkenyl
    0.35
    xsl
    0.35
     slightly
    0.34
    ispielsweise
    0.34
    是以
    0.33
    POSITIVE LOGITS
     пові
    0.44
    廃棄
    0.39
    Cycl
    0.37
    izes
    0.37
     avoid
    0.37
    丟
    0.37
    ҝ
    0.37
     проверя
    0.36
    atzeko
    0.36
    땅
    0.36
    Activations Density 0.057%

    No Known Activations