© 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. 169943
    Prev
    Next
    INDEX
    Explanations

    science, economics, systems explained

    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
    ufig
    0.50
    薬剤
    0.45
     ilaç
    0.44
    juvant
    0.43
    streetlight
    0.43
    కరించ
    0.43
    嘱
    0.43
    blastoma
    0.42
    蜇
    0.42
    drug
    0.42
    POSITIVE LOGITS
    <{
    0.43
     mechanics
    0.40
     doubles
    0.40
     Foo
    0.38
     system
    0.38
     economy
    0.37
     Buck
    0.37
    Content
    0.36
     mechanically
    0.36
     Bene
    0.36
    Activations Density 0.000%

    No Known Activations