© 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. 13084
    Prev
    Next
    INDEX
    Explanations

    restaurant food and location

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

    course for

    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
     نیز
    0.42
    Liste
    0.38
    桎
    0.36
     также
    0.35
    惴
    0.35
     Р
    0.34
    辩
    0.34
    В
    0.34
    вЂ
    0.34
    についても
    0.33
    POSITIVE LOGITS
     fiori
    0.42
     needed
    0.41
     ridges
    0.40
     everytime
    0.38
     corrugated
    0.38
     phosphorylated
    0.38
     walkway
    0.38
     dużo
    0.38
     নতুন
    0.38
    গঞ্জের
    0.37
    Activations Density 0.151%

    No Known Activations