© 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. 27577
    Prev
    Next
    INDEX
    Explanations

    table below or executive MBA

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

    Brutalism, cell, answers, publications

    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
    ED
    0.50
    #####
    0.50
    ਬ
    0.49
     አንዳንድ
    0.47
    Implement
    0.47
    Politics
    0.47
    Κ
    0.47
    キャップ
    0.47
    Π
    0.47
    Ý
    0.46
    POSITIVE LOGITS
     хвата
    0.52
     ford
    0.48
     maximization
    0.45
     refraction
    0.44
     flake
    0.44
     medial
    0.43
     trans
    0.43
     сложно
    0.43
     stochastic
    0.43
     получить
    0.42
    Activations Density 0.000%

    No Known Activations