© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134500
    Prev
    Next
    INDEX
    Explanations

    dreamed of narratives

    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_40_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
     gerekli
    0.43
    ້ອງ
    0.38
    োলন
    0.37
     লৌ
    0.37
     económ
    0.37
     『
    0.37
    equalTo
    0.36
    ையான
    0.36
     scriptlevel
    0.36
    ekte
    0.36
    POSITIVE LOGITS
    ی
    0.38
    britannien
    0.37
     group
    0.37
     narrativa
    0.36
    ikaze
    0.36
     grupp
    0.36
    badges
    0.35
     narratives
    0.35
    ร้าย
    0.35
    orth
    0.35
    Activations Density 0.000%

    No Known Activations