© 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. 31-GEMMASCOPE-2-RES-262K
    7. 48616
    Prev
    Next
    INDEX
    Explanations

    system administration commands

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     كرد
    0.49
    शन
    0.47
     სი
    0.47
    蘄
    0.47
    ంటీ
    0.45
    ्यूटर
    0.44
    シミ
    0.44
     άλλο
    0.44
     همچنین
    0.43
    хия
    0.43
    POSITIVE LOGITS
    x
    0.55
    ↵
    0.55
    stuff
    0.52
    w
    0.51
    ng
    0.50
    q
    0.50
    na
    0.48
    customers
    0.48
    ise
    0.47
    wood
    0.47
    Activations Density 0.001%

    No Known Activations