© 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. 6930
    Prev
    Next
    INDEX
    Explanations

    academic publications and institutions

    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
    தற்கு
    0.46
    ᐋ
    0.44
     стаття
    0.43
     ભા
    0.43
    зы
    0.43
     leçon
    0.42
     ຂ
    0.41
    ształ
    0.41
     élément
    0.41
    a
    0.41
    POSITIVE LOGITS
     busier
    0.39
    DEFG
    0.39
     busiest
    0.38
     countries
    0.38
     GET
    0.38
     کی۔
    0.37
    ™.
    0.37
    ーション
    0.37
    忙
    0.37
    ^{+}$.
    0.36
    Activations Density 0.060%

    No Known Activations