© 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. 5747
    Prev
    Next
    INDEX
    Explanations

    parenthesis followed by function

    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
     a
    0.75
     at
    0.54
     (
    0.53
    that
    0.52
    r
    0.52
    ר
    0.52
    ==
    0.52
    ayashi
    0.52
     {
    0.51
     \
    0.50
    POSITIVE LOGITS
    ев
    0.62
    ра
    0.61
    ла
    0.58
    ли
    0.52
    ethe
    0.52
    ัก
    0.50
     infrastructures
    0.49
     소재
    0.48
    ির
    0.48
    <0xD8>
    0.46
    Activations Density 0.507%

    No Known Activations