© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 4824
    Prev
    Next
    INDEX
    Explanations

    code and calculation elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    elten
    0.57
     ፍ
    0.55
     Europäischen
    0.52
     Гульнявыя
    0.52
    ро
    0.50
     ко
    0.49
     મળી
    0.49
     කා
    0.48
     предназначен
    0.48
    gün
    0.48
    POSITIVE LOGITS
    一
    0.58
    אם
    0.53
    _
    0.53
     altercation
    0.49
    一本
    0.49
    য
    0.48
     exec
    0.48
     halides
    0.47
    //
    0.47
    य
    0.46
    Activations Density 0.000%

    No Known Activations