© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21596
    Prev
    Next
    INDEX
    Explanations

    on its own

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ྣ
    0.47
    Sentiment
    0.35
    ू
    0.35
    επ
    0.35
    ారు
    0.33
    徹底
    0.33
    vergne
    0.33
     겨
    0.32
    žeme
    0.32
    సారి
    0.32
    POSITIVE LOGITS
     alone
    2.61
     itself
    2.50
    本身
    2.23
    alone
    2.17
     Alone
    2.16
    Alone
    2.02
     alleine
    1.98
     sozinho
    1.90
     allein
    1.88
     자체
    1.84
    Activations Density 0.005%

    No Known Activations