© 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. 144583
    Prev
    Next
    INDEX
    Explanations

    specific entities and actions

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

    forbidden words

    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
    忪
    0.46
     ipad
    0.43
     slam
    0.43
    nieuw
    0.42
    ందూ
    0.42
     teil
    0.41
    ለያዩ
    0.41
    #!/
    0.41
     mirror
    0.40
     scrapbook
    0.40
    POSITIVE LOGITS
     فی
    0.57
     liquors
    0.50
     maximization
    0.48
     गरेका
    0.47
    counterx
    0.46
     যাদের
    0.45
    factors
    0.45
    employed
    0.45
    ẹ
    0.45
    carbons
    0.45
    Activations Density 0.001%

    No Known Activations