© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4617
    Prev
    Next
    INDEX
    Explanations

    Singleton design pattern

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    as
    1.38
    and
    1.38
    d
    1.24
    at
    1.16
    ell
    1.06
    ar
    1.05
    ig
    1.01
     on
    1.00
    t
    0.99
    ab
    0.99
    POSITIVE LOGITS
     flamenco
    0.75
    녠
    0.70
     dogma
    0.70
     Paleo
    0.68
     masterful
    0.68
    ப்படுகிறது
    0.67
    น
    0.66
     monumental
    0.66
     palud
    0.66
     authorship
    0.66
    Activations Density 0.008%

    No Known Activations