© 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. 62304
    Prev
    Next
    INDEX
    Explanations

    less than

    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
    至少
    0.46
    搽
    0.45
     unrealistic
    0.41
    却没有
    0.40
    日下午
    0.38
     minst
    0.37
    دو
    0.37
    ưới
    0.37
    те
    0.37
    ведите
    0.36
    POSITIVE LOGITS
     $(<
    0.55
     ideale
    0.50
     (<
    0.49
    stellar
    0.49
    ideal
    0.46
     ideal
    0.44
     idéal
    0.43
     stellar
    0.42
     ideales
    0.41
    Ideal
    0.40
    Activations Density 0.009%

    No Known Activations