© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2660
    Prev
    Next
    INDEX
    Explanations

    company and discovery

    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_all/layer_41_width_262k_l0_big
    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
    ائص
    0.49
    យៈ
    0.48
    থমে
    0.48
     alterações
    0.47
     thoſe
    0.47
     whiche
    0.46
     führt
    0.46
     ـ
    0.46
    лями
    0.45
    ِمض
    0.45
    POSITIVE LOGITS
     formation
    0.64
     use
    0.62
     introduction
    0.57
     creation
    0.57
     Introduction
    0.57
     presence
    0.51
     Collapse
    0.51
     perpet
    0.49
     purchase
    0.49
     availability
    0.48
    Activations Density 0.010%

    No Known Activations