© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185582
    Prev
    Next
    INDEX
    Explanations

    both together

    np_acts-logits-general · gemini-2.5-flash-lite

    make marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     enquiry
    0.46
    针
    0.45
     Enquiry
    0.44
    摈
    0.44
    伦敦
    0.43
    躾
    0.43
     તથા
    0.43
    cı
    0.43
    伞
    0.42
     routinely
    0.42
    POSITIVE LOGITS
     these
    0.47
     codimension
    0.44
     Ngh
    0.43
     ligands
    0.42
     جسم
    0.42
     خاطر
    0.41
     ture
    0.41
     eros
    0.41
     manly
    0.41
     crocodile
    0.40
    Activations Density 0.001%

    No Known Activations