© 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. 186968
    Prev
    Next
    INDEX
    Explanations

    following punctuation or conjunctions

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

    life throws challenges

    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
     mora
    0.53
     FIV
    0.47
    .;
    0.46
     I
    0.44
    ান্ত
    0.44
     ABV
    0.43
     Fiverr
    0.43
     TCR
    0.41
     Moro
    0.41
     Advertiser
    0.41
    POSITIVE LOGITS
    WallArray
    0.47
    หย
    0.47
    抧
    0.47
     ponctué
    0.46
     rétréci
    0.46
     الهم
    0.46
    保证
    0.46
    cèle
    0.45
     پیسہ
    0.44
     ダ
    0.44
    Activations Density 0.001%

    No Known Activations