© 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. 228657
    Prev
    Next
    INDEX
    Explanations

    invisible and marginalized

    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
    चिक
    0.42
    虐
    0.42
    жному
    0.41
     injurious
    0.40
     ወይም
    0.40
     rupture
    0.39
     Бо
    0.39
     अथवा
    0.39
     dimulai
    0.38
    得意
    0.38
    POSITIVE LOGITS
     ব্যবহারের
    0.49
     usages
    0.46
     metter
    0.46
     verschillende
    0.44
    逐渐
    0.44
     якія
    0.43
     还
    0.43
    😟
    0.43
     这
    0.42
     использования
    0.42
    Activations Density 0.001%

    No Known Activations