© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31494
    Prev
    Next
    INDEX
    Explanations

    Punic Ports, inclusion criteria

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     أصبح
    0.57
    dynamic
    0.48
     ಘೋಷ
    0.45
     Ön
    0.45
     ক্রয়
    0.44
    탬
    0.44
     باستخدام
    0.43
    function
    0.43
     नमस्कार
    0.42
    addContainer
    0.42
    POSITIVE LOGITS
     resten
    0.47
     responsables
    0.44
    юро
    0.43
     pathophys
    0.43
    ะ
    0.43
     skele
    0.43
     sanitation
    0.41
     cole
    0.41
     insane
    0.40
    衛生
    0.40
    Activations Density 0.001%

    No Known Activations