© 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. 16949
    Prev
    Next
    INDEX
    Explanations

    events, conferences, forums, seminars

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

    conference, symposium, summit, forum

    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
     아래
    0.43
     scrollBody
    0.43
    お子
    0.41
    带有
    0.40
    谶
    0.39
     دارد
    0.38
     analges
    0.38
     বৈশিষ্ট্য
    0.38
     "/"
    0.38
     প্রকৃত
    0.38
    POSITIVE LOGITS
     Forum
    0.66
     Symposium
    0.66
     symposium
    0.66
     conference
    0.63
     konfer
    0.62
     forum
    0.61
    conference
    0.59
     सम्मेलन
    0.59
     seminar
    0.58
     фору
    0.58
    Activations Density 0.139%

    No Known Activations