© 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. 122816
    Prev
    Next
    INDEX
    Explanations

    Indian cities and regions

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

    Hinglish and Indian places

    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
     περιο
    0.48
     काल्पनिक
    0.47
     Österreich
    0.44
     γ
    0.43
     مِن
    0.43
     पीने
    0.42
     نظ
    0.42
     श्रद्धांजलि
    0.42
     рыб
    0.42
    OLYBDENUM
    0.42
    POSITIVE LOGITS
    India
    0.54
    Covid
    0.47
    South
    0.47
    Hyderabad
    0.47
    B
    0.46
    Department
    0.46
    Chennai
    0.46
    Governor
    0.45
    โต
    0.45
    都
    0.45
    Activations Density 0.001%

    No Known Activations