© 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. 187450
    Prev
    Next
    INDEX
    Explanations

    simultaneous or sequential presentations

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

    processes and descriptions

    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
     темпера
    0.55
     속에
    0.53
    лис
    0.52
     людей
    0.49
     макси
    0.49
     човек
    0.49
     ગે
    0.48
    萝
    0.47
    㩴
    0.47
     люд
    0.47
    POSITIVE LOGITS
     processes
    0.59
     implies
    0.57
     implementations
    0.52
     orchestration
    0.52
     actuation
    0.51
     inducing
    0.51
     imply
    0.50
     subprocess
    0.50
     occlusion
    0.49
     triggered
    0.49
    Activations Density 0.006%

    No Known Activations