© 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. 183237
    Prev
    Next
    INDEX
    Explanations

    roles after certain words

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

    legal terms and scenarios

    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
    Negative Logits
    ضيف
    0.53
    ంత్రి
    0.48
    ❻
    0.48
    கே
    0.47
    ächlich
    0.47
    창
    0.46
    ahuje
    0.46
    孩子
    0.46
    enfant
    0.46
     dziecko
    0.45
    POSITIVE LOGITS
     Plants
    0.54
     açıklam
    0.52
     IPS
    0.50
    )>
    0.48
     NaCl
    0.48
     والی
    0.47
    )?
    0.46
    IPTS
    0.46
     ASA
    0.44
     scandals
    0.44
    Activations Density 0.001%

    No Known Activations