© 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. 74761
    Prev
    Next
    INDEX
    Explanations

    process and outcome

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ちなみに
    0.48
    𝗿
    0.47
    𝗰
    0.46
    א
    0.45
    ्ल
    0.45
    ור
    0.45
    чів
    0.44
    ਾਰ
    0.44
    า
    0.44
    ಲಾ
    0.44
    POSITIVE LOGITS
     perpetuate
    0.42
     Heron
    0.42
     repet
    0.40
     Profesor
    0.40
     exacerbate
    0.39
     bienestar
    0.38
     worsen
    0.38
     deterior
    0.38
     souten
    0.38
     preponder
    0.38
    Activations Density 0.007%

    No Known Activations