© 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. 5040
    Prev
    Next
    INDEX
    Explanations

    just let me know or paste

    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
    0.53
     \
    0.42
     =
    0.40
     &
    0.39
     =>
    0.38
     (
    0.36
    D
    0.36
     ==
    0.36
    <0x0D>
    0.36
     table
    0.35
    POSITIVE LOGITS
    ᱝ
    0.44
    erà
    0.41
    اتب
    0.41
     actriz
    0.39
     تعلیم
    0.39
    ँच
    0.38
     члены
    0.38
    ຈັດສົ່ງ
    0.38
    ি
    0.37
     mức
    0.37
    Activations Density 0.101%

    No Known Activations