© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7564
    Prev
    Next
    INDEX
    Explanations

    India and tourism

    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_16k_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
    distan
    0.46
     अपार्टमेंट
    0.42
    샵
    0.40
     لاعب
    0.40
    Wales
    0.40
     आदान
    0.39
    앱
    0.39
     इंग्लैंड
    0.38
    Lyon
    0.38
    龍
    0.38
    POSITIVE LOGITS
     Ranchi
    0.52
    Kerala
    0.52
     kerala
    0.51
     Kerala
    0.50
     Allahabad
    0.48
     Jawaharlal
    0.48
     Uttarakhand
    0.48
    bollywood
    0.47
     கேரள
    0.47
     Shayari
    0.47
    Activations Density 0.109%

    No Known Activations