© 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. 22-GEMMASCOPE-2-RES-65K
    7. 6422
    Prev
    Next
    INDEX
    Explanations

    digital shadow, complex realities

    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_22_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
     /
    1.12
    /
    0.99
    )/
    0.98
     sử
    0.95
    /"
    0.94
    ).)
    0.88
     Uses
    0.88
     VERY
    0.88
    뻤
    0.87
     utilisant
    0.86
    POSITIVE LOGITS
     captivating
    1.32
     countless
    1.28
     bewild
    1.24
     bustling
    1.22
     dazzling
    1.21
     towering
    1.18
     myriad
    1.18
     sleek
    1.17
     perplexing
    1.15
     enthr
    1.15
    Activations Density 0.169%

    No Known Activations