© 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-65K
    7. 1902
    Prev
    Next
    INDEX
    Explanations

    superlative descriptions

    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
    Both
    0.28
     někter
    0.26
    。
    0.26
    的不同
    0.25
     thay
    0.25
     contradicts
    0.25
     nogle
    0.25
    禟
    0.25
     zowel
    0.24
    㳡
    0.24
    POSITIVE LOGITS
     easiest
    0.88
     simplest
    0.79
     most
    0.77
     quickest
    0.77
     clearest
    0.77
     safest
    0.77
     strongest
    0.76
     cleanest
    0.76
     biggest
    0.72
     healthiest
    0.72
    Activations Density 0.501%

    No Known Activations