© 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. 49847
    Prev
    Next
    INDEX
    Explanations

    evaluate language model

    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
    y
    0.52
    ler
    0.52
     economia
    0.50
     ecologists
    0.49
     stronger
    0.49
     economists
    0.48
     extremism
    0.47
     niños
    0.46
     prodotti
    0.46
     salariés
    0.45
    POSITIVE LOGITS
    addressed
    0.48
     Correctional
    0.45
    мель
    0.43
    னைய
    0.43
    )_{(
    0.42
     συνεχ
    0.42
    தைய
    0.42
     તથા
    0.41
     अशा
    0.41
    ながら
    0.41
    Activations Density 0.000%

    No Known Activations