© 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. 53-GEMMASCOPE-2-RES-262K
    7. 40991
    Prev
    Next
    INDEX
    Explanations

    on a massive

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     gigantes
    0.61
    无穷
    0.58
     gigante
    0.57
     giant
    0.55
    infinite
    0.55
    巨大的
    0.54
     infinite
    0.52
     gigantic
    0.52
     ogrom
    0.52
    巨
    0.51
    POSITIVE LOGITS
     absolute
    0.54
     Absolute
    0.53
    absolute
    0.48
    Absolute
    0.47
     absolutely
    0.46
     masses
    0.45
     Proper
    0.43
     absoluta
    0.43
     proper
    0.42
     Eye
    0.41
    Activations Density 0.006%

    No Known Activations