© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3755
    Prev
    Next
    INDEX
    Explanations

    reptiles and snakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
     Eureka
    0.93
     Mpc
    0.93
    萩
    0.93
     eureka
    0.84
    Eureka
    0.81
     Puch
    0.77
    苫
    0.76
    侑
    0.76
     suffrage
    0.75
    ុម
    0.74
    POSITIVE LOGITS
     snake
    3.25
     snakes
    3.13
     Snake
    2.94
    Snake
    2.83
     Snakes
    2.78
     reptile
    2.71
    snake
    2.67
     serpent
    2.59
     reptiles
    2.54
    🐍
    2.50
    Activations Density 0.145%

    No Known Activations