© 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. 2950
    Prev
    Next
    INDEX
    Explanations

    conjunctions and elaborations

    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
    ：
    0.46
     appartenant
    0.39
     loại
    0.37
    的时候
    0.36
     của
    0.36
    这一次
    0.36
     tejto
    0.35
    ،
    0.35
    堣
    0.34
    بيع
    0.33
    POSITIVE LOGITS
     மேலும்
    0.37
    并通过
    0.37
    represents
    0.36
     it
    0.36
     hence
    0.35
     எனவே
    0.35
     zudem
    0.35
    और
    0.35
    is
    0.34
    thus
    0.34
    Activations Density 0.004%

    No Known Activations