© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12271
    Prev
    Next
    INDEX
    Explanations

    between things or people

    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
     রাজশাহ
    0.42
    ிகளில்
    0.39
    ocarcinoma
    0.38
    खों
    0.38
     দলটি
    0.37
    ritional
    0.37
     各
    0.36
    在国内
    0.36
    образи
    0.36
    /*.
    0.35
    POSITIVE LOGITS
    他和
    0.91
     pairing
    0.87
    我和
    0.86
     antara
    0.80
     between
    0.76
     mellan
    0.75
    ระหว่าง
    0.74
     zwischen
    0.73
     giữa
    0.73
     между
    0.73
    Activations Density 0.075%

    No Known Activations