© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2029
    Prev
    Next
    INDEX
    Explanations

    python matplotlib code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     vandalism
    1.28
    ascin
    1.25
    |-\
    1.24
     burglar
    1.23
    ➜
    1.23
     predators
    1.23
     viruses
    1.23
     forcibly
    1.23
     }//
    1.22
     door
    1.22
    POSITIVE LOGITS
    Рас
    0.96
     Рас
    0.95
     Midd
    0.93
     Мі
    0.90
    Mixed
    0.90
     Сы
    0.89
     Pří
    0.88
     Hace
    0.86
     Сло
    0.85
     Mix
    0.84
    Activations Density 0.060%

    No Known Activations