© 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. 157639
    Prev
    Next
    INDEX
    Explanations

    increasingly litigious

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

    roleplay, job titles, classes

    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
    ここで
    0.48
    {//
    0.48
    цион
    0.48
    Tienes
    0.47
     redonde
    0.44
    श्रे
    0.43
    یط
    0.43
    arreglo
    0.43
    共通
    0.43
    witz
    0.43
    POSITIVE LOGITS
     zupeł
    0.48
     inspir
    0.48
     ת
    0.48
     rov
    0.47
     הי
    0.46
    ign
    0.45
    marin
    0.45
     пациен
    0.44
     Premiership
    0.44
     뭐
    0.44
    Activations Density 0.000%

    No Known Activations