© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30477
    Prev
    Next
    INDEX
    Explanations

    viewing or opening files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ឹក
    0.42
    FlowNode
    0.41
     gathers
    0.39
    tolower
    0.38
    তুম
    0.38
    ੲ
    0.38
     தேர்ந்தெடுக்க
    0.37
    ディション
    0.37
    }^{*}=
    0.37
     живело
    0.37
    POSITIVE LOGITS
     viewing
    1.22
     Viewing
    1.16
    Viewing
    1.16
     opening
    1.05
     viewer
    1.01
     Viewer
    1.00
     opened
    0.96
     Opening
    0.94
     просмотра
    0.93
     dibuka
    0.93
    Activations Density 0.003%

    No Known Activations