© 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. 154599
    Prev
    Next
    INDEX
    Explanations

    witnesses, type, everyone, leader

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

    moderate high effort

    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
    ar
    0.52
    edores
    0.49
    offic
    0.48
    or
    0.48
    o
    0.47
    বারের
    0.47
    ek
    0.46
    respon
    0.46
    event
    0.46
    ottom
    0.46
    POSITIVE LOGITS
     Ф
    0.48
     yù
    0.48
     polypeptides
    0.47
     Χ
    0.46
     типу
    0.46
     Б
    0.46
    णे
    0.45
     Verkehr
    0.45
     acrylate
    0.45
     التس
    0.44
    Activations Density 0.000%

    No Known Activations