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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133728
    Prev
    Next
    INDEX
    Explanations

    proof impression, mortgages loans, state abbreviations

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

    focused on skills

    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
     importing
    0.50
     any
    0.49
     which
    0.49
     people
    0.48
     N
    0.48
     up
    0.48
     Shel
    0.48
     /
    0.48
    I
    0.48
     those
    0.47
    POSITIVE LOGITS
    ști
    0.61
     dévo
    0.52
     божомолдору
    0.51
    ത്തിനായി
    0.49
    EndGlobalSection
    0.49
     unve
    0.48
     ছাড়া
    0.48
     গেরিলারা
    0.48
     consiguió
    0.48
    стави
    0.47
    Activations Density 0.000%

    No Known Activations