© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 88477
    Prev
    Next
    INDEX
    Explanations

    following testcaseprovisioning information

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific, technical, and economic terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंगली
    0.53
    घव
    0.46
     Και
    0.44
     Seperti
    0.43
    和我
    0.42
     Rồi
    0.42
    ≲
    0.42
    说
    0.41
    ítico
    0.41
    和他
    0.41
    POSITIVE LOGITS
     provision
    0.53
    informatics
    0.50
     these
    0.48
     provisioning
    0.48
     delivery
    0.47
     operation
    0.47
    provision
    0.47
     a
    0.46
     informatics
    0.46
     yerine
    0.46
    Activations Density 0.000%

    No Known Activations