© 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. 212146
    Prev
    Next
    INDEX
    Explanations

    afternoon and Industries Thrift call

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

    finding precise

    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
    Not in Any Lists

    No Comments

    Negative Logits
    imize
    0.48
     भाऊ
    0.48
     teslim
    0.45
     কপি
    0.44
     satire
    0.43
     spoof
    0.43
    害
    0.42
     দেবতা
    0.42
     deactivate
    0.41
     idiom
    0.41
    POSITIVE LOGITS
     piernas
    0.50
    غام
    0.49
     conduits
    0.48
     PLE
    0.48
    ・
    0.46
     glandes
    0.45
     fabri
    0.44
     fatores
    0.44
     Earnings
    0.43
     vestidos
    0.42
    Activations Density 0.000%

    No Known Activations