© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48052
    Prev
    Next
    INDEX
    Explanations

    your eyes

    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_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
    歟
    0.44
     weekends
    0.41
     cosmetology
    0.40
    Nc
    0.40
    賣
    0.40
     rewarding
    0.39
    ℠
    0.39
     merchandising
    0.39
    Aws
    0.39
    ᚨ
    0.39
    POSITIVE LOGITS
     observe
    0.42
    observe
    0.40
    usun
    0.38
    গন্ধ
    0.37
    өт
    0.37
     प्रतिबि
    0.37
     Observe
    0.36
    Observe
    0.36
    ዬ
    0.36
     Constit
    0.36
    Activations Density 0.001%

    No Known Activations