© 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. 53-GEMMASCOPE-2-RES-262K
    7. 12550
    Prev
    Next
    INDEX
    Explanations

    perfectly browned toast

    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_53_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
     waterfalls
    0.39
    ⚾
    0.38
     Бор
    0.38
    漓
    0.38
     Arund
    0.38
    中山
    0.37
    ໃ
    0.37
    龔
    0.37
    ൮
    0.37
    ಳಿತ
    0.36
    POSITIVE LOGITS
     toast
    3.73
     Toast
    3.47
    toast
    3.30
    Toast
    3.27
     toasts
    3.06
     toasted
    2.84
     toaster
    2.53
    toaster
    2.22
     tost
    2.19
     토
    1.75
    Activations Density 0.018%

    No Known Activations