© 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. 7916
    Prev
    Next
    INDEX
    Explanations

    premarital education and skills

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

    svinekjøtt, Predynastic, paraphilic

    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
     Nx
    0.29
     Wexford
    0.27
     Sox
    0.27
     Round
    0.26
    ς
    0.26
    s
    0.26
     Wembley
    0.26
    5
    0.25
     Accred
    0.25
     Robson
    0.25
    POSITIVE LOGITS
     مذکور
    0.28
    なのです
    0.25
     యొక్క
    0.25
    watering
    0.24
    ના
    0.24
    gium
    0.24
     שב
    0.23
     fondness
    0.23
    ಗೂ
    0.23
     そんな
    0.23
    Activations Density 0.228%

    No Known Activations