© 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-16K
    7. 10621
    Prev
    Next
    INDEX
    Explanations

    digit one

    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_16k_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
     აღმასრულებელი
    0.43
     Kopf
    0.41
     |
    0.41
     primeras
    0.39
              
    0.39
     Berl
    0.39
     primeiros
    0.38
     श्रेणी
    0.38
     primeiras
    0.38
     category
    0.38
    POSITIVE LOGITS
    1
    0.63
     ১
    0.62
    ⒈
    0.60
     १
    0.58
    １
    0.55
    ①
    0.54
     ۱
    0.54
    一是
    0.50
     ૧
    0.50
     ①
    0.49
    Activations Density 0.341%

    No Known Activations