© 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. 24776
    Prev
    Next
    INDEX
    Explanations

    Leverage, Monsters, intervention, tools, Pharma

    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
    Kra
    0.35
     SP
    0.35
    Verb
    0.35
     Verk
    0.35
    Church
    0.34
     Ver
    0.33
    ங்கில
    0.33
    ”—
    0.33
    nisse
    0.33
    慜
    0.33
    POSITIVE LOGITS
     unpredict
    0.44
     dizziness
    0.43
    ujourd
    0.43
     deteriorating
    0.42
     lament
    0.42
    डिंग
    0.41
     starved
    0.41
    飢
    0.41
     deteriorated
    0.41
     знаешь
    0.41
    Activations Density 0.000%

    No Known Activations