© 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-16K
    7. 6485
    Prev
    Next
    INDEX
    Explanations

    international organizations, UN agencies

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Newline
    0.54
    Dick
    0.52
    Pierce
    0.50
     pierce
    0.49
    LetterIndex
    0.48
    ModelGrid
    0.46
    incing
    0.46
    Evil
    0.46
     एनीमिया
    0.46
    ⓐ
    0.46
    POSITIVE LOGITS
     UNESCO
    0.81
     Unesco
    0.67
     ICT
    0.56
     secretariat
    0.55
    UNESCO
    0.54
     ILO
    0.53
     UNICEF
    0.52
     consultancy
    0.52
     UNHCR
    0.52
     Secretariat
    0.51
    Activations Density 0.117%

    No Known Activations