© 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. 50914
    Prev
    Next
    INDEX
    Explanations

    destruction, Russia, FIFA, range, rent

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

    explaining concepts or ideas

    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
    Not in Any Lists

    No Comments

    Negative Logits
     সত্ত্বেও
    0.46
    सामान्यीकृत
    0.44
    पेक्षा
    0.43
    批评
    0.42
     ويكي
    0.42
     তাপ
    0.41
    heureusement
    0.41
    缱
    0.41
     দুর্ভিক্ষের
    0.40
     Gameplay
    0.40
    POSITIVE LOGITS
    aki
    0.54
     to
    0.50
    ject
    0.50
    questa
    0.48
    jih
    0.47
     at
    0.45
     inh
    0.45
    tuk
    0.44
    artan
    0.43
    izem
    0.43
    Activations Density 0.000%

    No Known Activations