© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10081
    Prev
    Next
    INDEX
    Explanations

    kafka messages and topics

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

    message brokers and topics

    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_40_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
    lawn
    0.43
    hFile
    0.42
    Ꮐ
    0.40
    ScriptInterface
    0.40
    俎
    0.39
     عر
    0.39
     dexter
    0.39
    pron
    0.38
    🍬
    0.38
    dex
    0.38
    POSITIVE LOGITS
     kafka
    1.21
    Kafka
    1.20
     Kafka
    1.19
     Topic
    1.15
     topic
    1.14
    kafka
    1.14
    topic
    1.11
    Topic
    1.09
     topics
    1.05
     Topics
    1.03
    Activations Density 0.046%

    No Known Activations