© 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. 32386
    Prev
    Next
    INDEX
    Explanations

    transgender women, receptors, and serialization

    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
     চাহিয়
    0.39
     राजस्व
    0.37
    ೃತ
    0.37
    踟
    0.36
    कामना
    0.36
     почита
    0.35
    ionante
    0.35
     compensatory
    0.35
    PhotoMode
    0.35
    Ნ
    0.35
    POSITIVE LOGITS
     seria
    0.40
    resents
    0.39
     orphan
    0.39
     Swanson
    0.38
     hats
    0.37
    ANU
    0.36
     necess
    0.36
    ises
    0.36
    代表
    0.36
    ICA
    0.36
    Activations Density 0.000%

    No Known Activations