© 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. 247329
    Prev
    Next
    INDEX
    Explanations

    selling tickets and contributions

    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
     shortlisted
    0.49
    ඔ
    0.48
     chỉ
    0.45
     القسم
    0.45
    وبر
    0.45
    大学生
    0.45
    нут
    0.44
    ключение
    0.43
    辩
    0.42
    getInputStream
    0.42
    POSITIVE LOGITS
    NL
    0.42
     HIGH
    0.41
     Cav
    0.41
     OVER
    0.41
     Attractive
    0.41
     EF
    0.40
     LED
    0.40
    quita
    0.40
    gação
    0.40
     Entry
    0.40
    Activations Density 0.001%

    No Known Activations