© 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. 233530
    Prev
    Next
    INDEX
    Explanations

    conference call webcast presentation

    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
    である
    0.42
    وامل
    0.42
    yed
    0.41
    福祉
    0.41
     vicenda
    0.40
    個人
    0.40
     juf
    0.40
    祖
    0.40
     Caedwalla
    0.40
    antren
    0.39
    POSITIVE LOGITS
     presentation
    0.60
     présentation
    0.55
     Presentation
    0.55
     webcast
    0.54
    Presentation
    0.54
     presentations
    0.52
     apresentação
    0.52
     Presentations
    0.51
    Audio
    0.50
     Audio
    0.49
    Activations Density 0.033%

    No Known Activations