© 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. 40-GEMMASCOPE-2-RES-262K
    7. 3101
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    自身的
    0.26
    ленным
    0.25
     Andrei
    0.24
     থাকুন
    0.22
    叮
    0.22
     Maurizio
    0.22
    享
    0.21
    自身
    0.21
    باً
    0.21
     होऊ
    0.21
    POSITIVE LOGITS
    preprint
    0.32
    nof
    0.28
    submitted
    0.26
    JF
    0.25
     v
    0.25
     statistical
    0.25
     summit
    0.24
    text
    0.24
     submitted
    0.24
    tight
    0.24
    Activations Density 0.000%

    No Known Activations