© 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. 4149
    Prev
    Next
    INDEX
    Explanations

    technical terms and labels

    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
    <0x87>
    1.05
     Mandy
    1.04
     Zeke
    0.96
     norepinephrine
    0.96
     Niko
    0.95
     Confederate
    0.94
     Carrie
    0.92
     JPEG
    0.91
    NRC
    0.90
     glycerin
    0.89
    POSITIVE LOGITS
    electrical
    0.98
     ষ্ট
    0.95
     পোষ্ট
    0.94
    鎚
    0.94
     Kers
    0.91
     দিল্ল
    0.90
    åll
    0.88
    Electrical
    0.88
     Harlow
    0.88
     उत्तरप्रदेश
    0.87
    Activations Density 1.109%

    No Known Activations