© 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. 31-GEMMASCOPE-2-RES-262K
    7. 112335
    Prev
    Next
    INDEX
    Explanations

    packaging materials and designs

    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
     théra
    0.52
     transmutation
    0.48
     पीड़ा
    0.48
    騨
    0.48
    剧情
    0.47
    滤波
    0.46
     સ્વા
    0.46
     фаразы
    0.45
    舰
    0.45
     ব্যায়াম
    0.44
    POSITIVE LOGITS
     packaging
    1.01
     Packaging
    0.95
    Packaging
    0.86
    packaging
    0.86
    包装
    0.76
     printing
    0.75
     cardboard
    0.74
     cartons
    0.73
    印刷
    0.72
     Verpack
    0.71
    Activations Density 0.037%

    No Known Activations