© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14265
    Prev
    Next
    INDEX
    Explanations

    casino, review, table, bandwidth, canada

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

    Mark MVP Champion Lakers Mayor

    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_16k_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
    𝐮
    0.45
    SHARED
    0.43
    shared
    0.42
    homework
    0.42
    JSONObject
    0.41
    빈
    0.40
    ผล
    0.40
    वर्
    0.40
    policy
    0.39
    coupon
    0.39
    POSITIVE LOGITS
     PCP
    0.46
     MVP
    0.46
    }=\
    0.45
     Mark
    0.42
     Eduard
    0.42
     Terbaik
    0.42
     Loki
    0.41
     Gordo
    0.41
     Maha
    0.41
     Ecke
    0.41
    Activations Density 0.059%

    No Known Activations