© 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. 228770
    Prev
    Next
    INDEX
    Explanations

    locations and partnerships

    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
     Chipotle
    0.57
     Wholesale
    0.55
     p
    0.53
     Bronx
    0.52
     Yelp
    0.52
    EP
    0.50
    l
    0.49
    J
    0.49
     LSU
    0.49
    Џ
    0.48
    POSITIVE LOGITS
    ートン
    0.48
    今年の
    0.47
    documents
    0.47
    encript
    0.47
     نزدیک
    0.46
    макраты
    0.45
    人と
    0.45
    パートナー
    0.45
    今年は
    0.44
    وینت
    0.44
    Activations Density 0.001%

    No Known Activations