© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132798
    Prev
    Next
    INDEX
    Explanations

    joke setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鹼
    0.42
    <0x90>
    0.42
     TOG
    0.40
     потенциа
    0.40
    機會
    0.39
     enca
    0.39
    <0xA4>
    0.38
    <0xBD>
    0.37
     criação
    0.37
    潛
    0.37
    POSITIVE LOGITS
     Milling
    0.43
    ChooseServer
    0.42
     justifies
    0.40
     Loves
    0.40
    Long
    0.40
     Platform
    0.40
     Patrol
    0.40
     épouse
    0.39
     Worlds
    0.39
     Long
    0.38
    Activations Density 0.001%

    No Known Activations