© 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. 210372
    Prev
    Next
    INDEX
    Explanations

    to learn

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

    checking availability and proofreading

    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
    Sentiment
    0.62
    擂
    0.51
    Passing
    0.50
    stories
    0.50
    nios
    0.50
    stained
    0.49
    嘗
    0.48
    painting
    0.47
    稽
    0.46
    sentences
    0.45
    POSITIVE LOGITS
     berpeng
    0.55
     väik
    0.52
     vissa
    0.52
     sö
    0.51
     unele
    0.51
     masih
    0.50
     bazı
    0.50
     อิ
    0.50
     kompakt
    0.49
     일부
    0.48
    Activations Density 0.000%

    No Known Activations