© 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-262K
    7. 2653
    Prev
    Next
    INDEX
    Explanations

    Wikipedia articles or links

    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_262k_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
    customer
    0.44
    
    0.43
    fficient
    0.42
    女
    0.42
    Customer
    0.41
    Scatter
    0.41
     lotions
    0.41
    𝒞
    0.40
    
    0.40
    וּ
    0.40
    POSITIVE LOGITS
     Wikipedia
    1.96
     Wikiped
    1.90
     wikipedia
    1.77
    Wikipedia
    1.76
     wiki
    1.74
     Wiki
    1.71
    Wiki
    1.66
     Wikipédia
    1.63
     Wikimedia
    1.62
     wik
    1.62
    Activations Density 0.015%

    No Known Activations