© 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. 200222
    Prev
    Next
    INDEX
    Explanations

    common compound phrases

    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
    wenden
    0.50
    prar
    0.47
    
    0.46
    prin
    0.44
    estal
    0.44
     लॉन्
    0.44
    ナソニック
    0.43
     সিঙ্গ
    0.42
     ಏನು
    0.42
    filter
    0.42
    POSITIVE LOGITS
    د
    0.60
    ல
    0.59
     automata
    0.52
     vile
    0.48
     legume
    0.48
     potential
    0.48
    รก
    0.47
     dél
    0.47
     edilmiş
    0.46
     legumes
    0.46
    Activations Density 0.000%

    No Known Activations