© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125828
    Prev
    Next
    INDEX
    Explanations

    luxury fashion and locations

    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
    Ꮀ
    0.47
     Фургала
    0.45
     haunts
    0.45
     кого
    0.45
    一
    0.45
     harnesses
    0.44
     персонала
    0.44
    ्रिया
    0.43
     хал
    0.43
     దృష్టి
    0.42
    POSITIVE LOGITS
    \
    0.52
    z
    0.50
     Para
    0.49
     montant
    0.48
     Guide
    0.47
     Aruba
    0.46
     Alaska
    0.45
     bis
    0.45
     para
    0.45
     Offer
    0.45
    Activations Density 0.004%

    No Known Activations