© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6844
    Prev
    Next
    INDEX
    Explanations

    customer success

    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_31_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
     satisfacer
    0.59
    倫
    0.58
     maintenir
    0.57
    蘅
    0.53
    誠
    0.53
     soddis
    0.52
    健全
    0.49
    诚
    0.48
     migliorare
    0.48
    满足
    0.47
    POSITIVE LOGITS
     awful
    0.53
     Snapdragon
    0.51
     sassy
    0.51
     tiny
    0.50
     whopping
    0.49
     json
    0.49
     quirks
    0.49
     stories
    0.49
     profile
    0.49
     smudge
    0.48
    Activations Density 0.083%

    No Known Activations