© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49280
    Prev
    Next
    INDEX
    Explanations

    field training and research

    np_acts-logits-general · gemini-2.5-flash-lite

    countries or regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     তারাই
    0.50
    人们
    0.48
    ồm
    0.46
    tiden
    0.46
    大
    0.45
     કરો
    0.44
    什么
    0.43
    윳
    0.43
    事业
    0.43
     istedi
    0.42
    POSITIVE LOGITS
    ಗು
    0.43
     ಏಕೆಂದರೆ
    0.40
     श्रीलंका
    0.39
    orgh
    0.39
     Idha
    0.39
     Kef
    0.38
    annotation
    0.38
    र्य
    0.38
     Algeria
    0.38
     Jammu
    0.38
    Activations Density 0.000%

    No Known Activations