© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 952
    Prev
    Next
    INDEX
    Explanations

    code file beginnings

    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_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
     coached
    0.29
    ֿ
    0.28
     alken
    0.27
     abiotic
    0.27
     mashed
    0.26
     clogged
    0.26
     selectively
    0.26
     తయ
    0.26
     cannula
    0.25
    atoti
    0.25
    POSITIVE LOGITS
    #!/
    0.42
    import
    0.41
    <?
    0.38
    <%@
    0.35
    #
    0.35
    0.33
    0.33
    package
    0.32
    usepackage
    0.32
    $
    0.32
    Activations Density 0.113%

    No Known Activations