© 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-65K
    7. 48312
    Prev
    Next
    INDEX
    Explanations

    a choice or consequence

    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
     pione
    0.43
     topsail
    0.42
    懟
    0.41
     casks
    0.38
    ሦ
    0.38
    抨
    0.38
     prosp
    0.38
    োদ্ধ
    0.38
     princ
    0.38
     ಪ್ರತ
    0.37
    POSITIVE LOGITS
    <0x80>
    0.44
    \
    0.43
     and
    0.39
    ”
    0.37
    ми
    0.37
    ம்
    0.36
    wią
    0.36
    ,"
    0.36
    <0xE2>
    0.35
    ith
    0.35
    Activations Density 0.015%

    No Known Activations