© 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. 90457
    Prev
    Next
    INDEX
    Explanations

    establish

    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
    ari
    1.00
    ik
    0.88
    (\
    0.80
    ans
    0.77
    el
    0.76
    ole
    0.71
    ko
    0.68
    ,\"
    0.68
     t
    0.66
    ns
    0.65
    POSITIVE LOGITS
    establish
    0.88
    ્સ
    0.85
    ের
    0.80
    ς
    0.80
    માં
    0.77
     establish
    0.76
    ്
    0.75
    ों
    0.73
     براي
    0.70
     établ
    0.70
    Activations Density 0.005%

    No Known Activations