© 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. 142627
    Prev
    Next
    INDEX
    Explanations

    destroy, failures, ordinary, underperforming

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

    similarity, context, processing

    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
    ]+\
    0.44
     yüzde
    0.41
    ]=\
    0.40
     এইচডি
    0.40
     benzene
    0.40
     ನಾವು
    0.39
     warmed
    0.38
     quadrupole
    0.38
     ಅನುಪಾತ
    0.37
    ],'
    0.37
    POSITIVE LOGITS
    точ
    0.53
    ّ
    0.49
    podob
    0.46
    рони
    0.44
    奇怪
    0.42
    nicki
    0.42
    рована
    0.42
    亵
    0.42
    kob
    0.42
     Тре
    0.41
    Activations Density 0.001%

    No Known Activations