© 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. 188835
    Prev
    Next
    INDEX
    Explanations

    Western Australia

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

    programmed system with visuals

    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
    )^{[\
    0.49
    should
    0.48
    し
    0.48
    喪
    0.47
    感知
    0.46
    结构的
    0.46
    datum
    0.44
    ungsseite
    0.43
    completion
    0.43
    videmment
    0.43
    POSITIVE LOGITS
     પ્રથમ
    0.51
    नगर
    0.50
     raged
    0.50
     명령
    0.49
     saham
    0.47
     Kamane
    0.45
     Ә
    0.45
    विधि
    0.44
     sert
    0.44
    ಪಟ್ಟ
    0.44
    Activations Density 0.001%

    No Known Activations