© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94197
    Prev
    Next
    INDEX
    Explanations

    exploring new trying to say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ik
    0.53
     ću
    0.49
     Headquarters
    0.47
    $/../../../../
    0.47
     تنفيذ
    0.46
     ćemo
    0.46
     Pursuant
    0.46
    ä
    0.46
     पलट
    0.45
     खरी
    0.44
    POSITIVE LOGITS
     가지
    0.51
    ोषित
    0.51
    প্তাহ
    0.50
     flashes
    0.48
     topik
    0.48
     genders
    0.47
     tambah
    0.46
     lawyers
    0.45
     appart
    0.45
    最初は
    0.44
    Activations Density 0.005%

    No Known Activations