© 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. 203222
    Prev
    Next
    INDEX
    Explanations

    follow specific instructions

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

    memento, global health, immediate circumstances

    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
     How
    0.52
     Returns
    0.49
     under
    0.48
    .
    0.47
    C
    0.47
    tester
    0.46
    使用的
    0.46
     Liability
    0.45
     tester
    0.45
     ব্যবহার
    0.44
    POSITIVE LOGITS
     dajj
    0.53
    Metaxy
    0.51
     দার্শন
    0.50
    ਾਕ
    0.49
    ⌣
    0.49
     कार्तिक
    0.48
    㗆
    0.48
     പരിശീല
    0.47
    postos
    0.47
    ява
    0.46
    Activations Density 0.000%

    No Known Activations