© 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. 77948
    Prev
    Next
    INDEX
    Explanations

    marketing videos, available year, following descendants

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

    sequential numbers and ordered lists

    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
     तीस
    0.54
     அறை
    0.52
    B
    0.50
     பிரார்த்த
    0.49
     ích
    0.49
    三天
    0.48
     இடம்
    0.48
     ማ
    0.47
     मल्टीप्लाई
    0.47
     እንቅስቃሴ
    0.47
    POSITIVE LOGITS
    GTG
    0.51
    <sup>
    0.45
    츄
    0.45
     android
    0.43
    GLISH
    0.43
    ঙ্গি
    0.41
    जब
    0.41
     fontsize
    0.41
    만큼
    0.41
     oman
    0.40
    Activations Density 0.001%

    No Known Activations