© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48299
    Prev
    Next
    INDEX
    Explanations

    abilities. relationship. cards. aim. needed

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

    aim to present overview

    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
     করিতেছিল
    0.48
     从
    0.48
    rial
    0.48
    objClass
    0.46
     这是
    0.45
    ận
    0.44
     Blackjack
    0.44
     夏季
    0.44
     价
    0.43
    ulpt
    0.43
    POSITIVE LOGITS
     mision
    0.66
     philanthrop
    0.59
     pervasive
    0.55
     perpetuate
    0.52
     infrastrukt
    0.48
     pove
    0.48
     converge
    0.47
     endem
    0.47
     missionaries
    0.47
     crede
    0.47
    Activations Density 0.000%

    No Known Activations