© 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. 253034
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    on
    0.57
    am
    0.57
     on
    0.55
    Li
    0.55
    ib
    0.52
    żeń
    0.52
    oracle
    0.51
    ｎ
    0.50
    al
    0.50
    actions
    0.48
    POSITIVE LOGITS
     sugli
    0.44
     трудо
    0.43
     ajuste
    0.42
    тего
    0.42
     reto
    0.42
     resuspended
    0.42
     벡터
    0.41
     прекрасно
    0.41
    䧺
    0.41
    של
    0.40
    Activations Density 0.001%

    No Known Activations