© 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. 40763
    Prev
    Next
    INDEX
    Explanations

    сла/equations

    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
     Е
    0.46
     coefficients
    0.45
     Ε
    0.42
    arum
    0.42
     Eds
    0.42
    digits
    0.41
     coeff
    0.40
     केश
    0.40
    zeichen
    0.39
     Є
    0.39
    POSITIVE LOGITS
    ウ
    0.63
    乌
    0.61
     ur
    0.61
     ウ
    0.60
    Rav
    0.59
     우
    0.58
     rav
    0.57
    烏
    0.56
     rov
    0.55
     Rav
    0.52
    Activations Density 0.002%

    No Known Activations