© 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. 1679
    Prev
    Next
    INDEX
    Explanations

    sidebar containing 'News' and 'Favorites' tabs

    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
     FS
    0.32
     ___
    0.31
     --
    0.30
     --->
    0.30
     Mid
    0.29
     PS
    0.28
     CB
    0.28
     Lact
    0.28
     dx
    0.28
    可能是
    0.27
    POSITIVE LOGITS
    зайн
    0.28
    intai
    0.28
    seekers
    0.28
    duire
    0.28
     ”
    0.27
    طنين
    0.26
     profundizar
    0.26
    siye
    0.26
    soul
    0.26
     นิด
    0.26
    Activations Density 0.404%

    No Known Activations