© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82840
    Prev
    Next
    INDEX
    Explanations

    offer books

    np_acts-logits-general · gemini-2.5-flash-lite

    language or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ܂
    0.48
    <unused2169>
    0.46
    랙
    0.45
    鲵
    0.44
     αλλά
    0.43
     lắc
    0.41
    快递
    0.41
     ư
    0.40
     እና
    0.40
    έχ
    0.40
    POSITIVE LOGITS
    valor
    0.44
     honti
    0.43
     ஏற்படுத்து
    0.42
     secreto
    0.41
    por
    0.41
     dreadful
    0.40
     przede
    0.39
     pored
    0.39
     තුළ
    0.39
     divulge
    0.39
    Activations Density 0.002%

    No Known Activations